full-scale/corridor_curves.csv

algorithm,corridor_length,step,optimal_fraction
Committed Q-learning,5,1,0.2639999985694885
Committed Q-learning,5,2,0.20999999344348907
Committed Q-learning,5,3,0.12600000202655792
Committed Q-learning,5,4,0.06300000101327896
Committed Q-learning,5,5,0.03099999949336052
Committed Q-learning,5,6,0.07800000160932541
Committed Q-learning,5,7,0.23399999737739563
Committed Q-learning,5,8,0.2680000066757202
Committed Q-learning,5,9,0.2630000114440918
Committed Q-learning,5,10,0.24400000274181366
Committed Q-learning,5,11,0.18799999356269836
Committed Q-learning,5,12,0.16899999976158142
Committed Q-learning,5,13,0.2150000035762787
Committed Q-learning,5,14,0.2840000092983246
Committed Q-learning,5,15,0.3009999990463257
Committed Q-learning,5,16,0.30000001192092896
Committed Q-learning,5,17,0.3149999976158142
Committed Q-learning,5,18,0.31700000166893005
Committed Q-learning,5,19,0.31200000643730164
Committed Q-learning,5,20,0.33500000834465027
Committed Q-learning,5,21,0.3799999952316284
Committed Q-learning,5,22,0.38499999046325684
Committed Q-learning,5,23,0.39100000262260437
Committed Q-learning,5,24,0.42399999499320984
Committed Q-learning,5,25,0.4429999887943268
Committed Q-learning,5,26,0.4699999988079071
Committed Q-learning,5,27,0.492000013589859
Committed Q-learning,5,28,0.4959999918937683
Committed Q-learning,5,29,0.5299999713897705
Committed Q-learning,5,30,0.5400000214576721
Committed Q-learning,5,31,0.5709999799728394
Committed Q-learning,5,32,0.5879999995231628
Committed Q-learning,5,33,0.597000002861023
Committed Q-learning,5,34,0.628000020980835
Committed Q-learning,5,35,0.6340000033378601
Committed Q-learning,5,36,0.6520000100135803
Committed Q-learning,5,37,0.6669999957084656
Committed Q-learning,5,38,0.6819999814033508
Committed Q-learning,5,39,0.6970000267028809
Committed Q-learning,5,40,0.7160000205039978
Committed Q-learning,5,41,0.7329999804496765
Committed Q-learning,5,42,0.75
Committed Q-learning,5,43,0.7549999952316284
Committed Q-learning,5,44,0.781000018119812
Committed Q-learning,5,45,0.7979999780654907
Committed Q-learning,5,46,0.8050000071525574
Committed Q-learning,5,47,0.8220000267028809
Committed Q-learning,5,48,0.8259999752044678
Committed Q-learning,5,49,0.8479999899864197
Committed Q-learning,5,50,0.8510000109672546
Committed Q-learning,5,51,0.8640000224113464
Committed Q-learning,5,52,0.8820000290870667
Committed Q-learning,5,53,0.8920000195503235
Committed Q-learning,5,54,0.9049999713897705
Committed Q-learning,5,55,0.9110000133514404
Committed Q-learning,5,56,0.9269999861717224
Committed Q-learning,5,57,0.9350000023841858
Committed Q-learning,5,58,0.9490000009536743
Committed Q-learning,5,59,0.9599999785423279
Committed Q-learning,5,60,0.968999981880188
Committed Q-learning,5,61,0.9760000109672546
Committed Q-learning,5,62,0.9800000190734863
Committed Q-learning,5,63,0.984000027179718
Committed Q-learning,5,64,0.9869999885559082
Committed Q-learning,5,65,0.9879999756813049
Committed Q-learning,5,66,0.9890000224113464
Committed Q-learning,5,67,0.9900000095367432
Committed Q-learning,5,68,0.9940000176429749
Committed Q-learning,5,69,0.9940000176429749
Committed Q-learning,5,70,0.9950000047683716
Committed Q-learning,5,71,0.9959999918937683
Committed Q-learning,5,72,0.9980000257492065
Committed Q-learning,5,73,0.9980000257492065
Committed Q-learning,5,74,0.9980000257492065
Committed Q-learning,5,75,0.9980000257492065
Committed Q-learning,5,76,0.9990000128746033
Committed Q-learning,5,77,1.0
Committed Q-learning,5,78,1.0
Committed Q-learning,5,79,1.0
Committed Q-learning,5,80,1.0
Committed Q-learning,5,81,1.0
Committed Q-learning,5,82,1.0
Committed Q-learning,5,83,1.0
Committed Q-learning,5,84,1.0
Committed Q-learning,5,85,1.0
Committed Q-learning,5,86,1.0
Committed Q-learning,5,87,1.0
Committed Q-learning,5,88,1.0
Committed Q-learning,5,89,1.0
Committed Q-learning,5,90,1.0
Committed Q-learning,5,91,1.0
Committed Q-learning,5,92,1.0
Committed Q-learning,5,93,1.0
Committed Q-learning,5,94,1.0
Committed Q-learning,5,95,1.0
Committed Q-learning,5,96,1.0
Committed Q-learning,5,97,1.0
Committed Q-learning,5,98,1.0
Committed Q-learning,5,99,1.0
Committed Q-learning,5,100,1.0
Committed Q-learning,5,101,1.0
Committed Q-learning,5,102,1.0
Committed Q-learning,5,103,1.0
Committed Q-learning,5,104,1.0
Committed Q-learning,5,105,1.0
Committed Q-learning,5,106,1.0
Committed Q-learning,5,107,1.0
Committed Q-learning,5,108,1.0
Committed Q-learning,5,109,1.0
Committed Q-learning,5,110,1.0
Committed Q-learning,5,111,1.0
Committed Q-learning,5,112,1.0
Committed Q-learning,5,113,1.0
Committed Q-learning,5,114,1.0
Committed Q-learning,5,115,1.0
Committed Q-learning,5,116,1.0
Committed Q-learning,5,117,1.0
Committed Q-learning,5,118,1.0
Committed Q-learning,5,119,1.0
Committed Q-learning,5,120,1.0
Committed Q-learning,5,121,1.0
Committed Q-learning,5,122,1.0
Committed Q-learning,5,123,1.0
Committed Q-learning,5,124,1.0
Committed Q-learning,5,125,1.0
Committed Q-learning,5,126,1.0
Committed Q-learning,5,127,1.0
Committed Q-learning,5,128,1.0
Committed Q-learning,5,129,1.0
Committed Q-learning,5,130,1.0
Committed Q-learning,5,131,1.0
Committed Q-learning,5,132,1.0
Committed Q-learning,5,133,1.0
Committed Q-learning,5,134,1.0
Committed Q-learning,5,135,1.0
Committed Q-learning,5,136,1.0
Committed Q-learning,5,137,1.0
Committed Q-learning,5,138,1.0
Committed Q-learning,5,139,1.0
Committed Q-learning,5,140,1.0
Committed Q-learning,5,141,1.0
Committed Q-learning,5,142,1.0
Committed Q-learning,5,143,1.0
Committed Q-learning,5,144,1.0
Committed Q-learning,5,145,1.0
Committed Q-learning,5,146,1.0
Committed Q-learning,5,147,1.0
Committed Q-learning,5,148,1.0
Committed Q-learning,5,149,1.0
Committed Q-learning,5,150,1.0
Committed Q-learning,5,151,1.0
Committed Q-learning,5,152,1.0
Committed Q-learning,5,153,1.0
Committed Q-learning,5,154,1.0
Committed Q-learning,5,155,1.0
Committed Q-learning,5,156,1.0
Committed Q-learning,5,157,1.0
Committed Q-learning,5,158,1.0
Committed Q-learning,5,159,1.0
Committed Q-learning,5,160,1.0
Committed Q-learning,5,161,1.0
Committed Q-learning,5,162,1.0
Committed Q-learning,5,163,1.0
Committed Q-learning,5,164,1.0
Committed Q-learning,5,165,1.0
Committed Q-learning,5,166,1.0
Committed Q-learning,5,167,1.0
Committed Q-learning,5,168,1.0
Committed Q-learning,5,169,1.0
Committed Q-learning,5,170,1.0
Committed Q-learning,5,171,1.0
Committed Q-learning,5,172,1.0
Committed Q-learning,5,173,1.0
Committed Q-learning,5,174,1.0
Committed Q-learning,5,175,1.0
Committed Q-learning,5,176,1.0
Committed Q-learning,5,177,1.0
Committed Q-learning,5,178,1.0
Committed Q-learning,5,179,1.0
Committed Q-learning,5,180,1.0
Committed Q-learning,5,181,1.0
Committed Q-learning,5,182,1.0
Committed Q-learning,5,183,1.0
Committed Q-learning,5,184,1.0
Committed Q-learning,5,185,1.0
Committed Q-learning,5,186,1.0
Committed Q-learning,5,187,1.0
Committed Q-learning,5,188,1.0
Committed Q-learning,5,189,1.0
Committed Q-learning,5,190,1.0
Committed Q-learning,5,191,1.0
Committed Q-learning,5,192,1.0
Committed Q-learning,5,193,1.0
Committed Q-learning,5,194,1.0
Committed Q-learning,5,195,1.0
Committed Q-learning,5,196,1.0
Committed Q-learning,5,197,1.0
Committed Q-learning,5,198,1.0
Committed Q-learning,5,199,1.0
Committed Q-learning,5,200,1.0
Committed Q-learning,5,201,1.0
Committed Q-learning,5,202,1.0
Committed Q-learning,5,203,1.0
Committed Q-learning,5,204,1.0
Committed Q-learning,5,205,1.0
Committed Q-learning,5,206,1.0
Committed Q-learning,5,207,1.0
Committed Q-learning,5,208,1.0
Committed Q-learning,5,209,1.0
Committed Q-learning,5,210,1.0
Committed Q-learning,5,211,1.0
Committed Q-learning,5,212,1.0
Committed Q-learning,5,213,1.0
Committed Q-learning,5,214,1.0
Committed Q-learning,5,215,1.0
Committed Q-learning,5,216,1.0
Committed Q-learning,5,217,1.0
Committed Q-learning,5,218,1.0
Committed Q-learning,5,219,1.0
Committed Q-learning,5,220,1.0
Committed Q-learning,5,221,1.0
Committed Q-learning,5,222,1.0
Committed Q-learning,5,223,1.0
Committed Q-learning,5,224,1.0
Committed Q-learning,5,225,1.0
Committed Q-learning,5,226,1.0
Committed Q-learning,5,227,1.0
Committed Q-learning,5,228,1.0
Committed Q-learning,5,229,1.0
Committed Q-learning,5,230,1.0
Committed Q-learning,5,231,1.0
Committed Q-learning,5,232,1.0
Committed Q-learning,5,233,1.0
Committed Q-learning,5,234,1.0
Committed Q-learning,5,235,1.0
Committed Q-learning,5,236,1.0
Committed Q-learning,5,237,1.0
Committed Q-learning,5,238,1.0
Committed Q-learning,5,239,1.0
Committed Q-learning,5,240,1.0
Committed Q-learning,5,241,1.0
Committed Q-learning,5,242,1.0
Committed Q-learning,5,243,1.0
Committed Q-learning,5,244,1.0
Committed Q-learning,5,245,1.0
Committed Q-learning,5,246,1.0
Committed Q-learning,5,247,1.0
Committed Q-learning,5,248,1.0
Committed Q-learning,5,249,1.0
Committed Q-learning,5,250,1.0
Committed Q-learning,5,251,1.0
Committed Q-learning,5,252,1.0
Committed Q-learning,5,253,1.0
Committed Q-learning,5,254,1.0
Committed Q-learning,5,255,1.0
Committed Q-learning,5,256,1.0
Committed Q-learning,5,257,1.0
Committed Q-learning,5,258,1.0
Committed Q-learning,5,259,1.0
Committed Q-learning,5,260,1.0
Committed Q-learning,5,261,1.0
Committed Q-learning,5,262,1.0
Committed Q-learning,5,263,1.0
Committed Q-learning,5,264,1.0
Committed Q-learning,5,265,1.0
Committed Q-learning,5,266,1.0
Committed Q-learning,5,267,1.0
Committed Q-learning,5,268,1.0
Committed Q-learning,5,269,1.0
Committed Q-learning,5,270,1.0
Committed Q-learning,5,271,1.0
Committed Q-learning,5,272,1.0
Committed Q-learning,5,273,1.0
Committed Q-learning,5,274,1.0
Committed Q-learning,5,275,1.0
Committed Q-learning,5,276,1.0
Committed Q-learning,5,277,1.0
Committed Q-learning,5,278,1.0
Committed Q-learning,5,279,1.0
Committed Q-learning,5,280,1.0
Committed Q-learning,5,281,1.0
Committed Q-learning,5,282,1.0
Committed Q-learning,5,283,1.0
Committed Q-learning,5,284,1.0
Committed Q-learning,5,285,1.0
Committed Q-learning,5,286,1.0
Committed Q-learning,5,287,1.0
Committed Q-learning,5,288,1.0
Committed Q-learning,5,289,1.0
Committed Q-learning,5,290,1.0
Committed Q-learning,5,291,1.0
Committed Q-learning,5,292,1.0
Committed Q-learning,5,293,1.0
Committed Q-learning,5,294,1.0
Committed Q-learning,5,295,1.0
Committed Q-learning,5,296,1.0
Committed Q-learning,5,297,1.0
Committed Q-learning,5,298,1.0
Committed Q-learning,5,299,1.0
Committed Q-learning,5,300,1.0
Committed Q-learning,5,301,1.0
Committed Q-learning,5,302,1.0
Committed Q-learning,5,303,1.0
Committed Q-learning,5,304,1.0
Committed Q-learning,5,305,1.0
Committed Q-learning,5,306,1.0
Committed Q-learning,5,307,1.0
Committed Q-learning,5,308,1.0
Committed Q-learning,5,309,1.0
Committed Q-learning,5,310,1.0
Committed Q-learning,5,311,1.0
Committed Q-learning,5,312,1.0
Committed Q-learning,5,313,1.0
Committed Q-learning,5,314,1.0
Committed Q-learning,5,315,1.0
Committed Q-learning,5,316,1.0
Committed Q-learning,5,317,1.0
Committed Q-learning,5,318,1.0
Committed Q-learning,5,319,1.0
Committed Q-learning,5,320,1.0
Committed Q-learning,5,321,1.0
Committed Q-learning,5,322,1.0
Committed Q-learning,5,323,1.0
Committed Q-learning,5,324,1.0
Committed Q-learning,5,325,1.0
Committed Q-learning,5,326,1.0
Committed Q-learning,5,327,1.0
Committed Q-learning,5,328,1.0
Committed Q-learning,5,329,1.0
Committed Q-learning,5,330,1.0
Committed Q-learning,5,331,1.0
Committed Q-learning,5,332,1.0
Committed Q-learning,5,333,1.0
Committed Q-learning,5,334,1.0
Committed Q-learning,5,335,1.0
Committed Q-learning,5,336,1.0
Committed Q-learning,5,337,1.0
Committed Q-learning,5,338,1.0
Committed Q-learning,5,339,1.0
Committed Q-learning,5,340,1.0
Committed Q-learning,5,341,1.0
Committed Q-learning,5,342,1.0
Committed Q-learning,5,343,1.0
Committed Q-learning,5,344,1.0
Committed Q-learning,5,345,1.0
Committed Q-learning,5,346,1.0
Committed Q-learning,5,347,1.0
Committed Q-learning,5,348,1.0
Committed Q-learning,5,349,1.0
Committed Q-learning,5,350,1.0
Committed Q-learning,5,351,1.0
Committed Q-learning,5,352,1.0
Committed Q-learning,5,353,1.0
Committed Q-learning,5,354,1.0
Committed Q-learning,5,355,1.0
Committed Q-learning,5,356,1.0
Committed Q-learning,5,357,1.0
Committed Q-learning,5,358,1.0
Committed Q-learning,5,359,1.0
Committed Q-learning,5,360,1.0
Committed Q-learning,5,361,1.0
Committed Q-learning,5,362,1.0
Committed Q-learning,5,363,1.0
Committed Q-learning,5,364,1.0
Committed Q-learning,5,365,1.0
Committed Q-learning,5,366,1.0
Committed Q-learning,5,367,1.0
Committed Q-learning,5,368,1.0
Committed Q-learning,5,369,1.0
Committed Q-learning,5,370,1.0
Committed Q-learning,5,371,1.0
Committed Q-learning,5,372,1.0
Committed Q-learning,5,373,1.0
Committed Q-learning,5,374,1.0
Committed Q-learning,5,375,1.0
Committed Q-learning,5,376,1.0
Committed Q-learning,5,377,1.0
Committed Q-learning,5,378,1.0
Committed Q-learning,5,379,1.0
Committed Q-learning,5,380,1.0
Committed Q-learning,5,381,1.0
Committed Q-learning,5,382,1.0
Committed Q-learning,5,383,1.0
Committed Q-learning,5,384,1.0
Committed Q-learning,5,385,1.0
Committed Q-learning,5,386,1.0
Committed Q-learning,5,387,1.0
Committed Q-learning,5,388,1.0
Committed Q-learning,5,389,1.0
Committed Q-learning,5,390,1.0
Committed Q-learning,5,391,1.0
Committed Q-learning,5,392,1.0
Committed Q-learning,5,393,1.0
Committed Q-learning,5,394,1.0
Committed Q-learning,5,395,1.0
Committed Q-learning,5,396,1.0
Committed Q-learning,5,397,1.0
Committed Q-learning,5,398,1.0
Committed Q-learning,5,399,1.0
Committed Q-learning,5,400,1.0
Committed Q-learning,5,401,1.0
Committed Q-learning,5,402,1.0
Committed Q-learning,5,403,1.0
Committed Q-learning,5,404,1.0
Committed Q-learning,5,405,1.0
Committed Q-learning,5,406,1.0
Committed Q-learning,5,407,1.0
Committed Q-learning,5,408,1.0
Committed Q-learning,5,409,1.0
Committed Q-learning,5,410,1.0
Committed Q-learning,5,411,1.0
Committed Q-learning,5,412,1.0
Committed Q-learning,5,413,1.0
Committed Q-learning,5,414,1.0
Committed Q-learning,5,415,1.0
Committed Q-learning,5,416,1.0
Committed Q-learning,5,417,1.0
Committed Q-learning,5,418,1.0
Committed Q-learning,5,419,1.0
Committed Q-learning,5,420,1.0
Committed Q-learning,5,421,1.0
Committed Q-learning,5,422,1.0
Committed Q-learning,5,423,1.0
Committed Q-learning,5,424,1.0
Committed Q-learning,5,425,1.0
Committed Q-learning,5,426,1.0
Committed Q-learning,5,427,1.0
Committed Q-learning,5,428,1.0
Committed Q-learning,5,429,1.0
Committed Q-learning,5,430,1.0
Committed Q-learning,5,431,1.0
Committed Q-learning,5,432,1.0
Committed Q-learning,5,433,1.0
Committed Q-learning,5,434,1.0
Committed Q-learning,5,435,1.0
Committed Q-learning,5,436,1.0
Committed Q-learning,5,437,1.0
Committed Q-learning,5,438,1.0
Committed Q-learning,5,439,1.0
Committed Q-learning,5,440,1.0
Committed Q-learning,5,441,1.0
Committed Q-learning,5,442,1.0
Committed Q-learning,5,443,1.0
Committed Q-learning,5,444,1.0
Committed Q-learning,5,445,1.0
Committed Q-learning,5,446,1.0
Committed Q-learning,5,447,1.0
Committed Q-learning,5,448,1.0
Committed Q-learning,5,449,1.0
Committed Q-learning,5,450,1.0
Committed Q-learning,5,451,1.0
Committed Q-learning,5,452,1.0
Committed Q-learning,5,453,1.0
Committed Q-learning,5,454,1.0
Committed Q-learning,5,455,1.0
Committed Q-learning,5,456,1.0
Committed Q-learning,5,457,1.0
Committed Q-learning,5,458,1.0
Committed Q-learning,5,459,1.0
Committed Q-learning,5,460,1.0
Committed Q-learning,5,461,1.0
Committed Q-learning,5,462,1.0
Committed Q-learning,5,463,1.0
Committed Q-learning,5,464,1.0
Committed Q-learning,5,465,1.0
Committed Q-learning,5,466,1.0
Committed Q-learning,5,467,1.0
Committed Q-learning,5,468,1.0
Committed Q-learning,5,469,1.0
Committed Q-learning,5,470,1.0
Committed Q-learning,5,471,1.0
Committed Q-learning,5,472,1.0
Committed Q-learning,5,473,1.0
Committed Q-learning,5,474,1.0
Committed Q-learning,5,475,1.0
Committed Q-learning,5,476,1.0
Committed Q-learning,5,477,1.0
Committed Q-learning,5,478,1.0
Committed Q-learning,5,479,1.0
Committed Q-learning,5,480,1.0
Committed Q-learning,5,481,1.0
Committed Q-learning,5,482,1.0
Committed Q-learning,5,483,1.0
Committed Q-learning,5,484,1.0
Committed Q-learning,5,485,1.0
Committed Q-learning,5,486,1.0
Committed Q-learning,5,487,1.0
Committed Q-learning,5,488,1.0
Committed Q-learning,5,489,1.0
Committed Q-learning,5,490,1.0
Committed Q-learning,5,491,1.0
Committed Q-learning,5,492,1.0
Committed Q-learning,5,493,1.0
Committed Q-learning,5,494,1.0
Committed Q-learning,5,495,1.0
Committed Q-learning,5,496,1.0
Committed Q-learning,5,497,1.0
Committed Q-learning,5,498,1.0
Committed Q-learning,5,499,1.0
Committed Q-learning,5,500,1.0
Committed Q-learning,5,501,1.0
Committed Q-learning,5,502,1.0
Committed Q-learning,5,503,1.0
Committed Q-learning,5,504,1.0
Committed Q-learning,5,505,1.0
Committed Q-learning,5,506,1.0
Committed Q-learning,5,507,1.0
Committed Q-learning,5,508,1.0
Committed Q-learning,5,509,1.0
Committed Q-learning,5,510,1.0
Committed Q-learning,5,511,1.0
Committed Q-learning,5,512,1.0
Committed Q-learning,5,513,1.0
Committed Q-learning,5,514,1.0
Committed Q-learning,5,515,1.0
Committed Q-learning,5,516,1.0
Committed Q-learning,5,517,1.0
Committed Q-learning,5,518,1.0
Committed Q-learning,5,519,1.0
Committed Q-learning,5,520,1.0
Committed Q-learning,5,521,1.0
Committed Q-learning,5,522,1.0
Committed Q-learning,5,523,1.0
Committed Q-learning,5,524,1.0
Committed Q-learning,5,525,1.0
Committed Q-learning,5,526,1.0
Committed Q-learning,5,527,1.0
Committed Q-learning,5,528,1.0
Committed Q-learning,5,529,1.0
Committed Q-learning,5,530,1.0
Committed Q-learning,5,531,1.0
Committed Q-learning,5,532,1.0
Committed Q-learning,5,533,1.0
Committed Q-learning,5,534,1.0
Committed Q-learning,5,535,1.0
Committed Q-learning,5,536,1.0
Committed Q-learning,5,537,1.0
Committed Q-learning,5,538,1.0
Committed Q-learning,5,539,1.0
Committed Q-learning,5,540,1.0
Committed Q-learning,5,541,1.0
Committed Q-learning,5,542,1.0
Committed Q-learning,5,543,1.0
Committed Q-learning,5,544,1.0
Committed Q-learning,5,545,1.0
Committed Q-learning,5,546,1.0
Committed Q-learning,5,547,1.0
Committed Q-learning,5,548,1.0
Committed Q-learning,5,549,1.0
Committed Q-learning,5,550,1.0
Committed Q-learning,5,551,1.0
Committed Q-learning,5,552,1.0
Committed Q-learning,5,553,1.0
Committed Q-learning,5,554,1.0
Committed Q-learning,5,555,1.0
Committed Q-learning,5,556,1.0
Committed Q-learning,5,557,1.0
Committed Q-learning,5,558,1.0
Committed Q-learning,5,559,1.0
Committed Q-learning,5,560,1.0
Committed Q-learning,5,561,1.0
Committed Q-learning,5,562,1.0
Committed Q-learning,5,563,1.0
Committed Q-learning,5,564,1.0
Committed Q-learning,5,565,1.0
Committed Q-learning,5,566,1.0
Committed Q-learning,5,567,1.0
Committed Q-learning,5,568,1.0
Committed Q-learning,5,569,1.0
Committed Q-learning,5,570,1.0
Committed Q-learning,5,571,1.0
Committed Q-learning,5,572,1.0
Committed Q-learning,5,573,1.0
Committed Q-learning,5,574,1.0
Committed Q-learning,5,575,1.0
Committed Q-learning,5,576,1.0
Committed Q-learning,5,577,1.0
Committed Q-learning,5,578,1.0
Committed Q-learning,5,579,1.0
Committed Q-learning,5,580,1.0
Committed Q-learning,5,581,1.0
Committed Q-learning,5,582,1.0
Committed Q-learning,5,583,1.0
Committed Q-learning,5,584,1.0
Committed Q-learning,5,585,1.0
Committed Q-learning,5,586,1.0
Committed Q-learning,5,587,1.0
Committed Q-learning,5,588,1.0
Committed Q-learning,5,589,1.0
Committed Q-learning,5,590,1.0
Committed Q-learning,5,591,1.0
Committed Q-learning,5,592,1.0
Committed Q-learning,5,593,1.0
Committed Q-learning,5,594,1.0
Committed Q-learning,5,595,1.0
Committed Q-learning,5,596,1.0
Committed Q-learning,5,597,1.0
Committed Q-learning,5,598,1.0
Committed Q-learning,5,599,1.0
Committed Q-learning,5,600,1.0
Committed Q-learning,5,601,1.0
Committed Q-learning,5,602,1.0
Committed Q-learning,5,603,1.0
Committed Q-learning,5,604,1.0
Committed Q-learning,5,605,1.0
Committed Q-learning,5,606,1.0
Committed Q-learning,5,607,1.0
Committed Q-learning,5,608,1.0
Committed Q-learning,5,609,1.0
Committed Q-learning,5,610,1.0
Committed Q-learning,5,611,1.0
Committed Q-learning,5,612,1.0
Committed Q-learning,5,613,1.0
Committed Q-learning,5,614,1.0
Committed Q-learning,5,615,1.0
Committed Q-learning,5,616,1.0
Committed Q-learning,5,617,1.0
Committed Q-learning,5,618,1.0
Committed Q-learning,5,619,1.0
Committed Q-learning,5,620,1.0
Committed Q-learning,5,621,1.0
Committed Q-learning,5,622,1.0
Committed Q-learning,5,623,1.0
Committed Q-learning,5,624,1.0
Committed Q-learning,5,625,1.0
Committed Q-learning,5,626,1.0
Committed Q-learning,5,627,1.0
Committed Q-learning,5,628,1.0
Committed Q-learning,5,629,1.0
Committed Q-learning,5,630,1.0
Committed Q-learning,5,631,1.0
Committed Q-learning,5,632,1.0
Committed Q-learning,5,633,1.0
Committed Q-learning,5,634,1.0
Committed Q-learning,5,635,1.0
Committed Q-learning,5,636,1.0
Committed Q-learning,5,637,1.0
Committed Q-learning,5,638,1.0
Committed Q-learning,5,639,1.0
Committed Q-learning,5,640,1.0
Committed Q-learning,5,641,1.0
Committed Q-learning,5,642,1.0
Committed Q-learning,5,643,1.0
Committed Q-learning,5,644,1.0
Committed Q-learning,5,645,1.0
Committed Q-learning,5,646,1.0
Committed Q-learning,5,647,1.0
Committed Q-learning,5,648,1.0
Committed Q-learning,5,649,1.0
Committed Q-learning,5,650,1.0
Committed Q-learning,5,651,1.0
Committed Q-learning,5,652,1.0
Committed Q-learning,5,653,1.0
Committed Q-learning,5,654,1.0
Committed Q-learning,5,655,1.0
Committed Q-learning,5,656,1.0
Committed Q-learning,5,657,1.0
Committed Q-learning,5,658,1.0
Committed Q-learning,5,659,1.0
Committed Q-learning,5,660,1.0
Committed Q-learning,5,661,1.0
Committed Q-learning,5,662,1.0
Committed Q-learning,5,663,1.0
Committed Q-learning,5,664,1.0
Committed Q-learning,5,665,1.0
Committed Q-learning,5,666,1.0
Committed Q-learning,5,667,1.0
Committed Q-learning,5,668,1.0
Committed Q-learning,5,669,1.0
Committed Q-learning,5,670,1.0
Committed Q-learning,5,671,1.0
Committed Q-learning,5,672,1.0
Committed Q-learning,5,673,1.0
Committed Q-learning,5,674,1.0
Committed Q-learning,5,675,1.0
Committed Q-learning,5,676,1.0
Committed Q-learning,5,677,1.0
Committed Q-learning,5,678,1.0
Committed Q-learning,5,679,1.0
Committed Q-learning,5,680,1.0
Committed Q-learning,5,681,1.0
Committed Q-learning,5,682,1.0
Committed Q-learning,5,683,1.0
Committed Q-learning,5,684,1.0
Committed Q-learning,5,685,1.0
Committed Q-learning,5,686,1.0
Committed Q-learning,5,687,1.0
Committed Q-learning,5,688,1.0
Committed Q-learning,5,689,1.0
Committed Q-learning,5,690,1.0
Committed Q-learning,5,691,1.0
Committed Q-learning,5,692,1.0
Committed Q-learning,5,693,1.0
Committed Q-learning,5,694,1.0
Committed Q-learning,5,695,1.0
Committed Q-learning,5,696,1.0
Committed Q-learning,5,697,1.0
Committed Q-learning,5,698,1.0
Committed Q-learning,5,699,1.0
Committed Q-learning,5,700,1.0
Committed Q-learning,5,701,1.0
Committed Q-learning,5,702,1.0
Committed Q-learning,5,703,1.0
Committed Q-learning,5,704,1.0
Committed Q-learning,5,705,1.0
Committed Q-learning,5,706,1.0
Committed Q-learning,5,707,1.0
Committed Q-learning,5,708,1.0
Committed Q-learning,5,709,1.0
Committed Q-learning,5,710,1.0
Committed Q-learning,5,711,1.0
Committed Q-learning,5,712,1.0
Committed Q-learning,5,713,1.0
Committed Q-learning,5,714,1.0
Committed Q-learning,5,715,1.0
Committed Q-learning,5,716,1.0
Committed Q-learning,5,717,1.0
Committed Q-learning,5,718,1.0
Committed Q-learning,5,719,1.0
Committed Q-learning,5,720,1.0
Committed Q-learning,5,721,1.0
Committed Q-learning,5,722,1.0
Committed Q-learning,5,723,1.0
Committed Q-learning,5,724,1.0
Committed Q-learning,5,725,1.0
Committed Q-learning,5,726,1.0
Committed Q-learning,5,727,1.0
Committed Q-learning,5,728,1.0
Committed Q-learning,5,729,1.0
Committed Q-learning,5,730,1.0
Committed Q-learning,5,731,1.0
Committed Q-learning,5,732,1.0
Committed Q-learning,5,733,1.0
Committed Q-learning,5,734,1.0
Committed Q-learning,5,735,1.0
Committed Q-learning,5,736,1.0
Committed Q-learning,5,737,1.0
Committed Q-learning,5,738,1.0
Committed Q-learning,5,739,1.0
Committed Q-learning,5,740,1.0
Committed Q-learning,5,741,1.0
Committed Q-learning,5,742,1.0
Committed Q-learning,5,743,1.0
Committed Q-learning,5,744,1.0
Committed Q-learning,5,745,1.0
Committed Q-learning,5,746,1.0
Committed Q-learning,5,747,1.0
Committed Q-learning,5,748,1.0
Committed Q-learning,5,749,1.0
Committed Q-learning,5,750,1.0
Committed Q-learning,5,751,1.0
Committed Q-learning,5,752,1.0
Committed Q-learning,5,753,1.0
Committed Q-learning,5,754,1.0
Committed Q-learning,5,755,1.0
Committed Q-learning,5,756,1.0
Committed Q-learning,5,757,1.0
Committed Q-learning,5,758,1.0
Committed Q-learning,5,759,1.0
Committed Q-learning,5,760,1.0
Committed Q-learning,5,761,1.0
Committed Q-learning,5,762,1.0
Committed Q-learning,5,763,1.0
Committed Q-learning,5,764,1.0
Committed Q-learning,5,765,1.0
Committed Q-learning,5,766,1.0
Committed Q-learning,5,767,1.0
Committed Q-learning,5,768,1.0
Committed Q-learning,5,769,1.0
Committed Q-learning,5,770,1.0
Committed Q-learning,5,771,1.0
Committed Q-learning,5,772,1.0
Committed Q-learning,5,773,1.0
Committed Q-learning,5,774,1.0
Committed Q-learning,5,775,1.0
Committed Q-learning,5,776,1.0
Committed Q-learning,5,777,1.0
Committed Q-learning,5,778,1.0
Committed Q-learning,5,779,1.0
Committed Q-learning,5,780,1.0
Committed Q-learning,5,781,1.0
Committed Q-learning,5,782,1.0
Committed Q-learning,5,783,1.0
Committed Q-learning,5,784,1.0
Committed Q-learning,5,785,1.0
Committed Q-learning,5,786,1.0
Committed Q-learning,5,787,1.0
Committed Q-learning,5,788,1.0
Committed Q-learning,5,789,1.0
Committed Q-learning,5,790,1.0
Committed Q-learning,5,791,1.0
Committed Q-learning,5,792,1.0
Committed Q-learning,5,793,1.0
Committed Q-learning,5,794,1.0
Committed Q-learning,5,795,1.0
Committed Q-learning,5,796,1.0
Committed Q-learning,5,797,1.0
Committed Q-learning,5,798,1.0
Committed Q-learning,5,799,1.0
Committed Q-learning,5,800,1.0
Committed Q-learning,5,801,1.0
Committed Q-learning,5,802,1.0
Committed Q-learning,5,803,1.0
Committed Q-learning,5,804,1.0
Committed Q-learning,5,805,1.0
Committed Q-learning,5,806,1.0
Committed Q-learning,5,807,1.0
Committed Q-learning,5,808,1.0
Committed Q-learning,5,809,1.0
Committed Q-learning,5,810,1.0
Committed Q-learning,5,811,1.0
Committed Q-learning,5,812,1.0
Committed Q-learning,5,813,1.0
Committed Q-learning,5,814,1.0
Committed Q-learning,5,815,1.0
Committed Q-learning,5,816,1.0
Committed Q-learning,5,817,1.0
Committed Q-learning,5,818,1.0
Committed Q-learning,5,819,1.0
Committed Q-learning,5,820,1.0
Committed Q-learning,5,821,1.0
Committed Q-learning,5,822,1.0
Committed Q-learning,5,823,1.0
Committed Q-learning,5,824,1.0
Committed Q-learning,5,825,1.0
Committed Q-learning,5,826,1.0
Committed Q-learning,5,827,1.0
Committed Q-learning,5,828,1.0
Committed Q-learning,5,829,1.0
Committed Q-learning,5,830,1.0
Committed Q-learning,5,831,1.0
Committed Q-learning,5,832,1.0
Committed Q-learning,5,833,1.0
Committed Q-learning,5,834,1.0
Committed Q-learning,5,835,1.0
Committed Q-learning,5,836,1.0
Committed Q-learning,5,837,1.0
Committed Q-learning,5,838,1.0
Committed Q-learning,5,839,1.0
Committed Q-learning,5,840,1.0
Committed Q-learning,5,841,1.0
Committed Q-learning,5,842,1.0
Committed Q-learning,5,843,1.0
Committed Q-learning,5,844,1.0
Committed Q-learning,5,845,1.0
Committed Q-learning,5,846,1.0
Committed Q-learning,5,847,1.0
Committed Q-learning,5,848,1.0
Committed Q-learning,5,849,1.0
Committed Q-learning,5,850,1.0
Committed Q-learning,5,851,1.0
Committed Q-learning,5,852,1.0
Committed Q-learning,5,853,1.0
Committed Q-learning,5,854,1.0
Committed Q-learning,5,855,1.0
Committed Q-learning,5,856,1.0
Committed Q-learning,5,857,1.0
Committed Q-learning,5,858,1.0
Committed Q-learning,5,859,1.0
Committed Q-learning,5,860,1.0
Committed Q-learning,5,861,1.0
Committed Q-learning,5,862,1.0
Committed Q-learning,5,863,1.0
Committed Q-learning,5,864,1.0
Committed Q-learning,5,865,1.0
Committed Q-learning,5,866,1.0
Committed Q-learning,5,867,1.0
Committed Q-learning,5,868,1.0
Committed Q-learning,5,869,1.0
Committed Q-learning,5,870,1.0
Committed Q-learning,5,871,1.0
Committed Q-learning,5,872,1.0
Committed Q-learning,5,873,1.0
Committed Q-learning,5,874,1.0
Committed Q-learning,5,875,1.0
Committed Q-learning,5,876,1.0
Committed Q-learning,5,877,1.0
Committed Q-learning,5,878,1.0
Committed Q-learning,5,879,1.0
Committed Q-learning,5,880,1.0
Committed Q-learning,5,881,1.0
Committed Q-learning,5,882,1.0
Committed Q-learning,5,883,1.0
Committed Q-learning,5,884,1.0
Committed Q-learning,5,885,1.0
Committed Q-learning,5,886,1.0
Committed Q-learning,5,887,1.0
Committed Q-learning,5,888,1.0
Committed Q-learning,5,889,1.0
Committed Q-learning,5,890,1.0
Committed Q-learning,5,891,1.0
Committed Q-learning,5,892,1.0
Committed Q-learning,5,893,1.0
Committed Q-learning,5,894,1.0
Committed Q-learning,5,895,1.0
Committed Q-learning,5,896,1.0
Committed Q-learning,5,897,1.0
Committed Q-learning,5,898,1.0
Committed Q-learning,5,899,1.0
Committed Q-learning,5,900,1.0
Committed Q-learning,5,901,1.0
Committed Q-learning,5,902,1.0
Committed Q-learning,5,903,1.0
Committed Q-learning,5,904,1.0
Committed Q-learning,5,905,1.0
Committed Q-learning,5,906,1.0
Committed Q-learning,5,907,1.0
Committed Q-learning,5,908,1.0
Committed Q-learning,5,909,1.0
Committed Q-learning,5,910,1.0
Committed Q-learning,5,911,1.0
Committed Q-learning,5,912,1.0
Committed Q-learning,5,913,1.0
Committed Q-learning,5,914,1.0
Committed Q-learning,5,915,1.0
Committed Q-learning,5,916,1.0
Committed Q-learning,5,917,1.0
Committed Q-learning,5,918,1.0
Committed Q-learning,5,919,1.0
Committed Q-learning,5,920,1.0
Committed Q-learning,5,921,1.0
Committed Q-learning,5,922,1.0
Committed Q-learning,5,923,1.0
Committed Q-learning,5,924,1.0
Committed Q-learning,5,925,1.0
Committed Q-learning,5,926,1.0
Committed Q-learning,5,927,1.0
Committed Q-learning,5,928,1.0
Committed Q-learning,5,929,1.0
Committed Q-learning,5,930,1.0
Committed Q-learning,5,931,1.0
Committed Q-learning,5,932,1.0
Committed Q-learning,5,933,1.0
Committed Q-learning,5,934,1.0
Committed Q-learning,5,935,1.0
Committed Q-learning,5,936,1.0
Committed Q-learning,5,937,1.0
Committed Q-learning,5,938,1.0
Committed Q-learning,5,939,1.0
Committed Q-learning,5,940,1.0
Committed Q-learning,5,941,1.0
Committed Q-learning,5,942,1.0
Committed Q-learning,5,943,1.0
Committed Q-learning,5,944,1.0
Committed Q-learning,5,945,1.0
Committed Q-learning,5,946,1.0
Committed Q-learning,5,947,1.0
Committed Q-learning,5,948,1.0
Committed Q-learning,5,949,1.0
Committed Q-learning,5,950,1.0
Committed Q-learning,5,951,1.0
Committed Q-learning,5,952,1.0
Committed Q-learning,5,953,1.0
Committed Q-learning,5,954,1.0
Committed Q-learning,5,955,1.0
Committed Q-learning,5,956,1.0
Committed Q-learning,5,957,1.0
Committed Q-learning,5,958,1.0
Committed Q-learning,5,959,1.0
Committed Q-learning,5,960,1.0
Committed Q-learning,5,961,1.0
Committed Q-learning,5,962,1.0
Committed Q-learning,5,963,1.0
Committed Q-learning,5,964,1.0
Committed Q-learning,5,965,1.0
Committed Q-learning,5,966,1.0
Committed Q-learning,5,967,1.0
Committed Q-learning,5,968,1.0
Committed Q-learning,5,969,1.0
Committed Q-learning,5,970,1.0
Committed Q-learning,5,971,1.0
Committed Q-learning,5,972,1.0
Committed Q-learning,5,973,1.0
Committed Q-learning,5,974,1.0
Committed Q-learning,5,975,1.0
Committed Q-learning,5,976,1.0
Committed Q-learning,5,977,1.0
Committed Q-learning,5,978,1.0
Committed Q-learning,5,979,1.0
Committed Q-learning,5,980,1.0
Committed Q-learning,5,981,1.0
Committed Q-learning,5,982,1.0
Committed Q-learning,5,983,1.0
Committed Q-learning,5,984,1.0
Committed Q-learning,5,985,1.0
Committed Q-learning,5,986,1.0
Committed Q-learning,5,987,1.0
Committed Q-learning,5,988,1.0
Committed Q-learning,5,989,1.0
Committed Q-learning,5,990,1.0
Committed Q-learning,5,991,1.0
Committed Q-learning,5,992,1.0
Committed Q-learning,5,993,1.0
Committed Q-learning,5,994,1.0
Committed Q-learning,5,995,1.0
Committed Q-learning,5,996,1.0
Committed Q-learning,5,997,1.0
Committed Q-learning,5,998,1.0
Committed Q-learning,5,999,1.0
Committed Q-learning,5,1000,1.0
Committed Q-learning,10,1,0.2590000033378601
Committed Q-learning,10,2,0.20100000500679016
Committed Q-learning,10,3,0.12200000137090683
Committed Q-learning,10,4,0.054999999701976776
Committed Q-learning,10,5,0.03700000047683716
Committed Q-learning,10,6,0.032999999821186066
Committed Q-learning,10,7,0.027000000700354576
Committed Q-learning,10,8,0.024000000208616257
Committed Q-learning,10,9,0.020999999716877937
Committed Q-learning,10,10,0.019999999552965164
Committed Q-learning,10,11,0.08500000089406967
Committed Q-learning,10,12,0.23000000417232513
Committed Q-learning,10,13,0.2980000078678131
Committed Q-learning,10,14,0.3269999921321869
Committed Q-learning,10,15,0.33500000834465027
Committed Q-learning,10,16,0.33799999952316284
Committed Q-learning,10,17,0.3370000123977661
Committed Q-learning,10,18,0.296999990940094
Committed Q-learning,10,19,0.20600000023841858
Committed Q-learning,10,20,0.15399999916553497
Committed Q-learning,10,21,0.13199999928474426
Committed Q-learning,10,22,0.1379999965429306
Committed Q-learning,10,23,0.22300000488758087
Committed Q-learning,10,24,0.3269999921321869
Committed Q-learning,10,25,0.38999998569488525
Committed Q-learning,10,26,0.43799999356269836
Committed Q-learning,10,27,0.4790000021457672
Committed Q-learning,10,28,0.4950000047683716
Committed Q-learning,10,29,0.515999972820282
Committed Q-learning,10,30,0.5220000147819519
Committed Q-learning,10,31,0.4740000069141388
Committed Q-learning,10,32,0.41499999165534973
Committed Q-learning,10,33,0.3619999885559082
Committed Q-learning,10,34,0.382999986410141
Committed Q-learning,10,35,0.42500001192092896
Committed Q-learning,10,36,0.4970000088214874
Committed Q-learning,10,37,0.5360000133514404
Committed Q-learning,10,38,0.5559999942779541
Committed Q-learning,10,39,0.5899999737739563
Committed Q-learning,10,40,0.6159999966621399
Committed Q-learning,10,41,0.6439999938011169
Committed Q-learning,10,42,0.6669999957084656
Committed Q-learning,10,43,0.6620000004768372
Committed Q-learning,10,44,0.625
Committed Q-learning,10,45,0.6100000143051147
Committed Q-learning,10,46,0.6190000176429749
Committed Q-learning,10,47,0.6439999938011169
Committed Q-learning,10,48,0.6660000085830688
Committed Q-learning,10,49,0.6840000152587891
Committed Q-learning,10,50,0.7210000157356262
Committed Q-learning,10,51,0.722000002861023
Committed Q-learning,10,52,0.7490000128746033
Committed Q-learning,10,53,0.7770000100135803
Committed Q-learning,10,54,0.796999990940094
Committed Q-learning,10,55,0.8050000071525574
Committed Q-learning,10,56,0.8109999895095825
Committed Q-learning,10,57,0.8209999799728394
Committed Q-learning,10,58,0.8309999704360962
Committed Q-learning,10,59,0.843999981880188
Committed Q-learning,10,60,0.8379999995231628
Committed Q-learning,10,61,0.8569999933242798
Committed Q-learning,10,62,0.8579999804496765
Committed Q-learning,10,63,0.8679999709129333
Committed Q-learning,10,64,0.8849999904632568
Committed Q-learning,10,65,0.8920000195503235
Committed Q-learning,10,66,0.902999997138977
Committed Q-learning,10,67,0.902999997138977
Committed Q-learning,10,68,0.9160000085830688
Committed Q-learning,10,69,0.9160000085830688
Committed Q-learning,10,70,0.9369999766349792
Committed Q-learning,10,71,0.9399999976158142
Committed Q-learning,10,72,0.9430000185966492
Committed Q-learning,10,73,0.9480000138282776
Committed Q-learning,10,74,0.9470000267028809
Committed Q-learning,10,75,0.9490000009536743
Committed Q-learning,10,76,0.949999988079071
Committed Q-learning,10,77,0.953000009059906
Committed Q-learning,10,78,0.9610000252723694
Committed Q-learning,10,79,0.9620000123977661
Committed Q-learning,10,80,0.9660000205039978
Committed Q-learning,10,81,0.972000002861023
Committed Q-learning,10,82,0.9779999852180481
Committed Q-learning,10,83,0.9789999723434448
Committed Q-learning,10,84,0.9829999804496765
Committed Q-learning,10,85,0.9850000143051147
Committed Q-learning,10,86,0.9869999885559082
Committed Q-learning,10,87,0.9850000143051147
Committed Q-learning,10,88,0.9860000014305115
Committed Q-learning,10,89,0.9860000014305115
Committed Q-learning,10,90,0.9879999756813049
Committed Q-learning,10,91,0.9879999756813049
Committed Q-learning,10,92,0.9890000224113464
Committed Q-learning,10,93,0.9919999837875366
Committed Q-learning,10,94,0.9919999837875366
Committed Q-learning,10,95,0.9929999709129333
Committed Q-learning,10,96,0.9929999709129333
Committed Q-learning,10,97,0.9929999709129333
Committed Q-learning,10,98,0.9940000176429749
Committed Q-learning,10,99,0.9940000176429749
Committed Q-learning,10,100,0.9940000176429749
Committed Q-learning,10,101,0.9940000176429749
Committed Q-learning,10,102,0.996999979019165
Committed Q-learning,10,103,0.996999979019165
Committed Q-learning,10,104,0.9959999918937683
Committed Q-learning,10,105,0.9959999918937683
Committed Q-learning,10,106,0.9959999918937683
Committed Q-learning,10,107,0.9959999918937683
Committed Q-learning,10,108,0.9959999918937683
Committed Q-learning,10,109,0.9959999918937683
Committed Q-learning,10,110,0.9959999918937683
Committed Q-learning,10,111,0.9959999918937683
Committed Q-learning,10,112,0.9959999918937683
Committed Q-learning,10,113,0.996999979019165
Committed Q-learning,10,114,0.9980000257492065
Committed Q-learning,10,115,0.9990000128746033
Committed Q-learning,10,116,1.0
Committed Q-learning,10,117,1.0
Committed Q-learning,10,118,1.0
Committed Q-learning,10,119,1.0
Committed Q-learning,10,120,1.0
Committed Q-learning,10,121,1.0
Committed Q-learning,10,122,0.9990000128746033
Committed Q-learning,10,123,0.9990000128746033
Committed Q-learning,10,124,0.9990000128746033
Committed Q-learning,10,125,0.9990000128746033
Committed Q-learning,10,126,0.9990000128746033
Committed Q-learning,10,127,0.9990000128746033
Committed Q-learning,10,128,0.9990000128746033
Committed Q-learning,10,129,0.9990000128746033
Committed Q-learning,10,130,0.9990000128746033
Committed Q-learning,10,131,0.9990000128746033
Committed Q-learning,10,132,0.9990000128746033
Committed Q-learning,10,133,1.0
Committed Q-learning,10,134,1.0
Committed Q-learning,10,135,1.0
Committed Q-learning,10,136,1.0
Committed Q-learning,10,137,1.0
Committed Q-learning,10,138,1.0
Committed Q-learning,10,139,1.0
Committed Q-learning,10,140,1.0
Committed Q-learning,10,141,1.0
Committed Q-learning,10,142,1.0
Committed Q-learning,10,143,1.0
Committed Q-learning,10,144,1.0
Committed Q-learning,10,145,1.0
Committed Q-learning,10,146,1.0
Committed Q-learning,10,147,1.0
Committed Q-learning,10,148,1.0
Committed Q-learning,10,149,1.0
Committed Q-learning,10,150,1.0
Committed Q-learning,10,151,1.0
Committed Q-learning,10,152,1.0
Committed Q-learning,10,153,1.0
Committed Q-learning,10,154,1.0
Committed Q-learning,10,155,1.0
Committed Q-learning,10,156,1.0
Committed Q-learning,10,157,1.0
Committed Q-learning,10,158,1.0
Committed Q-learning,10,159,1.0
Committed Q-learning,10,160,1.0
Committed Q-learning,10,161,1.0
Committed Q-learning,10,162,1.0
Committed Q-learning,10,163,1.0
Committed Q-learning,10,164,1.0
Committed Q-learning,10,165,1.0
Committed Q-learning,10,166,1.0
Committed Q-learning,10,167,1.0
Committed Q-learning,10,168,1.0
Committed Q-learning,10,169,1.0
Committed Q-learning,10,170,1.0
Committed Q-learning,10,171,1.0
Committed Q-learning,10,172,1.0
Committed Q-learning,10,173,1.0
Committed Q-learning,10,174,1.0
Committed Q-learning,10,175,1.0
Committed Q-learning,10,176,1.0
Committed Q-learning,10,177,1.0
Committed Q-learning,10,178,1.0
Committed Q-learning,10,179,1.0
Committed Q-learning,10,180,1.0
Committed Q-learning,10,181,1.0
Committed Q-learning,10,182,1.0
Committed Q-learning,10,183,1.0
Committed Q-learning,10,184,1.0
Committed Q-learning,10,185,1.0
Committed Q-learning,10,186,1.0
Committed Q-learning,10,187,1.0
Committed Q-learning,10,188,1.0
Committed Q-learning,10,189,1.0
Committed Q-learning,10,190,1.0
Committed Q-learning,10,191,1.0
Committed Q-learning,10,192,1.0
Committed Q-learning,10,193,1.0
Committed Q-learning,10,194,1.0
Committed Q-learning,10,195,1.0
Committed Q-learning,10,196,1.0
Committed Q-learning,10,197,1.0
Committed Q-learning,10,198,1.0
Committed Q-learning,10,199,1.0
Committed Q-learning,10,200,1.0
Committed Q-learning,10,201,1.0
Committed Q-learning,10,202,1.0
Committed Q-learning,10,203,1.0
Committed Q-learning,10,204,1.0
Committed Q-learning,10,205,1.0
Committed Q-learning,10,206,1.0
Committed Q-learning,10,207,1.0
Committed Q-learning,10,208,1.0
Committed Q-learning,10,209,1.0
Committed Q-learning,10,210,1.0
Committed Q-learning,10,211,1.0
Committed Q-learning,10,212,1.0
Committed Q-learning,10,213,1.0
Committed Q-learning,10,214,1.0
Committed Q-learning,10,215,1.0
Committed Q-learning,10,216,1.0
Committed Q-learning,10,217,1.0
Committed Q-learning,10,218,1.0
Committed Q-learning,10,219,1.0
Committed Q-learning,10,220,1.0
Committed Q-learning,10,221,1.0
Committed Q-learning,10,222,1.0
Committed Q-learning,10,223,1.0
Committed Q-learning,10,224,1.0
Committed Q-learning,10,225,1.0
Committed Q-learning,10,226,1.0
Committed Q-learning,10,227,1.0
Committed Q-learning,10,228,1.0
Committed Q-learning,10,229,1.0
Committed Q-learning,10,230,1.0
Committed Q-learning,10,231,1.0
Committed Q-learning,10,232,1.0
Committed Q-learning,10,233,1.0
Committed Q-learning,10,234,1.0
Committed Q-learning,10,235,1.0
Committed Q-learning,10,236,1.0
Committed Q-learning,10,237,1.0
Committed Q-learning,10,238,1.0
Committed Q-learning,10,239,1.0
Committed Q-learning,10,240,1.0
Committed Q-learning,10,241,1.0
Committed Q-learning,10,242,1.0
Committed Q-learning,10,243,1.0
Committed Q-learning,10,244,1.0
Committed Q-learning,10,245,1.0
Committed Q-learning,10,246,1.0
Committed Q-learning,10,247,1.0
Committed Q-learning,10,248,1.0
Committed Q-learning,10,249,1.0
Committed Q-learning,10,250,1.0
Committed Q-learning,10,251,1.0
Committed Q-learning,10,252,1.0
Committed Q-learning,10,253,1.0
Committed Q-learning,10,254,1.0
Committed Q-learning,10,255,1.0
Committed Q-learning,10,256,1.0
Committed Q-learning,10,257,1.0
Committed Q-learning,10,258,1.0
Committed Q-learning,10,259,1.0
Committed Q-learning,10,260,1.0
Committed Q-learning,10,261,1.0
Committed Q-learning,10,262,1.0
Committed Q-learning,10,263,1.0
Committed Q-learning,10,264,1.0
Committed Q-learning,10,265,1.0
Committed Q-learning,10,266,1.0
Committed Q-learning,10,267,1.0
Committed Q-learning,10,268,1.0
Committed Q-learning,10,269,1.0
Committed Q-learning,10,270,1.0
Committed Q-learning,10,271,1.0
Committed Q-learning,10,272,1.0
Committed Q-learning,10,273,1.0
Committed Q-learning,10,274,1.0
Committed Q-learning,10,275,1.0
Committed Q-learning,10,276,1.0
Committed Q-learning,10,277,1.0
Committed Q-learning,10,278,1.0
Committed Q-learning,10,279,1.0
Committed Q-learning,10,280,1.0
Committed Q-learning,10,281,1.0
Committed Q-learning,10,282,1.0
Committed Q-learning,10,283,1.0
Committed Q-learning,10,284,1.0
Committed Q-learning,10,285,1.0
Committed Q-learning,10,286,1.0
Committed Q-learning,10,287,1.0
Committed Q-learning,10,288,1.0
Committed Q-learning,10,289,1.0
Committed Q-learning,10,290,1.0
Committed Q-learning,10,291,1.0
Committed Q-learning,10,292,1.0
Committed Q-learning,10,293,1.0
Committed Q-learning,10,294,1.0
Committed Q-learning,10,295,1.0
Committed Q-learning,10,296,1.0
Committed Q-learning,10,297,1.0
Committed Q-learning,10,298,1.0
Committed Q-learning,10,299,1.0
Committed Q-learning,10,300,1.0
Committed Q-learning,10,301,1.0
Committed Q-learning,10,302,1.0
Committed Q-learning,10,303,1.0
Committed Q-learning,10,304,1.0
Committed Q-learning,10,305,1.0
Committed Q-learning,10,306,1.0
Committed Q-learning,10,307,1.0
Committed Q-learning,10,308,1.0
Committed Q-learning,10,309,1.0
Committed Q-learning,10,310,1.0
Committed Q-learning,10,311,1.0
Committed Q-learning,10,312,1.0
Committed Q-learning,10,313,1.0
Committed Q-learning,10,314,1.0
Committed Q-learning,10,315,1.0
Committed Q-learning,10,316,1.0
Committed Q-learning,10,317,1.0
Committed Q-learning,10,318,1.0
Committed Q-learning,10,319,1.0
Committed Q-learning,10,320,1.0
Committed Q-learning,10,321,1.0
Committed Q-learning,10,322,1.0
Committed Q-learning,10,323,1.0
Committed Q-learning,10,324,1.0
Committed Q-learning,10,325,1.0
Committed Q-learning,10,326,1.0
Committed Q-learning,10,327,1.0
Committed Q-learning,10,328,1.0
Committed Q-learning,10,329,1.0
Committed Q-learning,10,330,1.0
Committed Q-learning,10,331,1.0
Committed Q-learning,10,332,1.0
Committed Q-learning,10,333,1.0
Committed Q-learning,10,334,1.0
Committed Q-learning,10,335,1.0
Committed Q-learning,10,336,1.0
Committed Q-learning,10,337,1.0
Committed Q-learning,10,338,1.0
Committed Q-learning,10,339,1.0
Committed Q-learning,10,340,1.0
Committed Q-learning,10,341,1.0
Committed Q-learning,10,342,1.0
Committed Q-learning,10,343,1.0
Committed Q-learning,10,344,1.0
Committed Q-learning,10,345,1.0
Committed Q-learning,10,346,1.0
Committed Q-learning,10,347,1.0
Committed Q-learning,10,348,1.0
Committed Q-learning,10,349,1.0
Committed Q-learning,10,350,1.0
Committed Q-learning,10,351,1.0
Committed Q-learning,10,352,1.0
Committed Q-learning,10,353,1.0
Committed Q-learning,10,354,1.0
Committed Q-learning,10,355,1.0
Committed Q-learning,10,356,1.0
Committed Q-learning,10,357,1.0
Committed Q-learning,10,358,1.0
Committed Q-learning,10,359,1.0
Committed Q-learning,10,360,1.0
Committed Q-learning,10,361,1.0
Committed Q-learning,10,362,1.0
Committed Q-learning,10,363,1.0
Committed Q-learning,10,364,1.0
Committed Q-learning,10,365,1.0
Committed Q-learning,10,366,1.0
Committed Q-learning,10,367,1.0
Committed Q-learning,10,368,1.0
Committed Q-learning,10,369,1.0
Committed Q-learning,10,370,1.0
Committed Q-learning,10,371,1.0
Committed Q-learning,10,372,1.0
Committed Q-learning,10,373,1.0
Committed Q-learning,10,374,1.0
Committed Q-learning,10,375,1.0
Committed Q-learning,10,376,1.0
Committed Q-learning,10,377,1.0
Committed Q-learning,10,378,1.0
Committed Q-learning,10,379,1.0
Committed Q-learning,10,380,1.0
Committed Q-learning,10,381,1.0
Committed Q-learning,10,382,1.0
Committed Q-learning,10,383,1.0
Committed Q-learning,10,384,1.0
Committed Q-learning,10,385,1.0
Committed Q-learning,10,386,1.0
Committed Q-learning,10,387,1.0
Committed Q-learning,10,388,1.0
Committed Q-learning,10,389,1.0
Committed Q-learning,10,390,1.0
Committed Q-learning,10,391,1.0
Committed Q-learning,10,392,1.0
Committed Q-learning,10,393,1.0
Committed Q-learning,10,394,1.0
Committed Q-learning,10,395,1.0
Committed Q-learning,10,396,1.0
Committed Q-learning,10,397,1.0
Committed Q-learning,10,398,1.0
Committed Q-learning,10,399,1.0
Committed Q-learning,10,400,1.0
Committed Q-learning,10,401,1.0
Committed Q-learning,10,402,1.0
Committed Q-learning,10,403,1.0
Committed Q-learning,10,404,1.0
Committed Q-learning,10,405,1.0
Committed Q-learning,10,406,1.0
Committed Q-learning,10,407,1.0
Committed Q-learning,10,408,1.0
Committed Q-learning,10,409,1.0
Committed Q-learning,10,410,1.0
Committed Q-learning,10,411,1.0
Committed Q-learning,10,412,1.0
Committed Q-learning,10,413,1.0
Committed Q-learning,10,414,1.0
Committed Q-learning,10,415,1.0
Committed Q-learning,10,416,1.0
Committed Q-learning,10,417,1.0
Committed Q-learning,10,418,1.0
Committed Q-learning,10,419,1.0
Committed Q-learning,10,420,1.0
Committed Q-learning,10,421,1.0
Committed Q-learning,10,422,1.0
Committed Q-learning,10,423,1.0
Committed Q-learning,10,424,1.0
Committed Q-learning,10,425,1.0
Committed Q-learning,10,426,1.0
Committed Q-learning,10,427,1.0
Committed Q-learning,10,428,1.0
Committed Q-learning,10,429,1.0
Committed Q-learning,10,430,1.0
Committed Q-learning,10,431,1.0
Committed Q-learning,10,432,1.0
Committed Q-learning,10,433,1.0
Committed Q-learning,10,434,1.0
Committed Q-learning,10,435,1.0
Committed Q-learning,10,436,1.0
Committed Q-learning,10,437,1.0
Committed Q-learning,10,438,1.0
Committed Q-learning,10,439,1.0
Committed Q-learning,10,440,1.0
Committed Q-learning,10,441,1.0
Committed Q-learning,10,442,1.0
Committed Q-learning,10,443,1.0
Committed Q-learning,10,444,1.0
Committed Q-learning,10,445,1.0
Committed Q-learning,10,446,1.0
Committed Q-learning,10,447,1.0
Committed Q-learning,10,448,1.0
Committed Q-learning,10,449,1.0
Committed Q-learning,10,450,1.0
Committed Q-learning,10,451,1.0
Committed Q-learning,10,452,1.0
Committed Q-learning,10,453,1.0
Committed Q-learning,10,454,1.0
Committed Q-learning,10,455,1.0
Committed Q-learning,10,456,1.0
Committed Q-learning,10,457,1.0
Committed Q-learning,10,458,1.0
Committed Q-learning,10,459,1.0
Committed Q-learning,10,460,1.0
Committed Q-learning,10,461,1.0
Committed Q-learning,10,462,1.0
Committed Q-learning,10,463,1.0
Committed Q-learning,10,464,1.0
Committed Q-learning,10,465,1.0
Committed Q-learning,10,466,1.0
Committed Q-learning,10,467,1.0
Committed Q-learning,10,468,1.0
Committed Q-learning,10,469,1.0
Committed Q-learning,10,470,1.0
Committed Q-learning,10,471,1.0
Committed Q-learning,10,472,1.0
Committed Q-learning,10,473,1.0
Committed Q-learning,10,474,1.0
Committed Q-learning,10,475,1.0
Committed Q-learning,10,476,1.0
Committed Q-learning,10,477,1.0
Committed Q-learning,10,478,1.0
Committed Q-learning,10,479,1.0
Committed Q-learning,10,480,1.0
Committed Q-learning,10,481,1.0
Committed Q-learning,10,482,1.0
Committed Q-learning,10,483,1.0
Committed Q-learning,10,484,1.0
Committed Q-learning,10,485,1.0
Committed Q-learning,10,486,1.0
Committed Q-learning,10,487,1.0
Committed Q-learning,10,488,1.0
Committed Q-learning,10,489,1.0
Committed Q-learning,10,490,1.0
Committed Q-learning,10,491,1.0
Committed Q-learning,10,492,1.0
Committed Q-learning,10,493,1.0
Committed Q-learning,10,494,1.0
Committed Q-learning,10,495,1.0
Committed Q-learning,10,496,1.0
Committed Q-learning,10,497,1.0
Committed Q-learning,10,498,1.0
Committed Q-learning,10,499,1.0
Committed Q-learning,10,500,1.0
Committed Q-learning,10,501,1.0
Committed Q-learning,10,502,1.0
Committed Q-learning,10,503,1.0
Committed Q-learning,10,504,1.0
Committed Q-learning,10,505,1.0
Committed Q-learning,10,506,1.0
Committed Q-learning,10,507,1.0
Committed Q-learning,10,508,1.0
Committed Q-learning,10,509,1.0
Committed Q-learning,10,510,1.0
Committed Q-learning,10,511,1.0
Committed Q-learning,10,512,1.0
Committed Q-learning,10,513,1.0
Committed Q-learning,10,514,1.0
Committed Q-learning,10,515,1.0
Committed Q-learning,10,516,1.0
Committed Q-learning,10,517,1.0
Committed Q-learning,10,518,1.0
Committed Q-learning,10,519,1.0
Committed Q-learning,10,520,1.0
Committed Q-learning,10,521,1.0
Committed Q-learning,10,522,1.0
Committed Q-learning,10,523,1.0
Committed Q-learning,10,524,1.0
Committed Q-learning,10,525,1.0
Committed Q-learning,10,526,1.0
Committed Q-learning,10,527,1.0
Committed Q-learning,10,528,1.0
Committed Q-learning,10,529,1.0
Committed Q-learning,10,530,1.0
Committed Q-learning,10,531,1.0
Committed Q-learning,10,532,1.0
Committed Q-learning,10,533,1.0
Committed Q-learning,10,534,1.0
Committed Q-learning,10,535,1.0
Committed Q-learning,10,536,1.0
Committed Q-learning,10,537,1.0
Committed Q-learning,10,538,1.0
Committed Q-learning,10,539,1.0
Committed Q-learning,10,540,1.0
Committed Q-learning,10,541,1.0
Committed Q-learning,10,542,1.0
Committed Q-learning,10,543,1.0
Committed Q-learning,10,544,1.0
Committed Q-learning,10,545,1.0
Committed Q-learning,10,546,1.0
Committed Q-learning,10,547,1.0
Committed Q-learning,10,548,1.0
Committed Q-learning,10,549,1.0
Committed Q-learning,10,550,1.0
Committed Q-learning,10,551,1.0
Committed Q-learning,10,552,1.0
Committed Q-learning,10,553,1.0
Committed Q-learning,10,554,1.0
Committed Q-learning,10,555,1.0
Committed Q-learning,10,556,1.0
Committed Q-learning,10,557,1.0
Committed Q-learning,10,558,1.0
Committed Q-learning,10,559,1.0
Committed Q-learning,10,560,1.0
Committed Q-learning,10,561,1.0
Committed Q-learning,10,562,1.0
Committed Q-learning,10,563,1.0
Committed Q-learning,10,564,1.0
Committed Q-learning,10,565,1.0
Committed Q-learning,10,566,1.0
Committed Q-learning,10,567,1.0
Committed Q-learning,10,568,1.0
Committed Q-learning,10,569,1.0
Committed Q-learning,10,570,1.0
Committed Q-learning,10,571,1.0
Committed Q-learning,10,572,1.0
Committed Q-learning,10,573,1.0
Committed Q-learning,10,574,1.0
Committed Q-learning,10,575,1.0
Committed Q-learning,10,576,1.0
Committed Q-learning,10,577,1.0
Committed Q-learning,10,578,1.0
Committed Q-learning,10,579,1.0
Committed Q-learning,10,580,1.0
Committed Q-learning,10,581,1.0
Committed Q-learning,10,582,1.0
Committed Q-learning,10,583,1.0
Committed Q-learning,10,584,1.0
Committed Q-learning,10,585,1.0
Committed Q-learning,10,586,1.0
Committed Q-learning,10,587,1.0
Committed Q-learning,10,588,1.0
Committed Q-learning,10,589,1.0
Committed Q-learning,10,590,1.0
Committed Q-learning,10,591,1.0
Committed Q-learning,10,592,1.0
Committed Q-learning,10,593,1.0
Committed Q-learning,10,594,1.0
Committed Q-learning,10,595,1.0
Committed Q-learning,10,596,1.0
Committed Q-learning,10,597,1.0
Committed Q-learning,10,598,1.0
Committed Q-learning,10,599,1.0
Committed Q-learning,10,600,1.0
Committed Q-learning,10,601,1.0
Committed Q-learning,10,602,1.0
Committed Q-learning,10,603,1.0
Committed Q-learning,10,604,1.0
Committed Q-learning,10,605,1.0
Committed Q-learning,10,606,1.0
Committed Q-learning,10,607,1.0
Committed Q-learning,10,608,1.0
Committed Q-learning,10,609,1.0
Committed Q-learning,10,610,1.0
Committed Q-learning,10,611,1.0
Committed Q-learning,10,612,1.0
Committed Q-learning,10,613,1.0
Committed Q-learning,10,614,1.0
Committed Q-learning,10,615,1.0
Committed Q-learning,10,616,1.0
Committed Q-learning,10,617,1.0
Committed Q-learning,10,618,1.0
Committed Q-learning,10,619,1.0
Committed Q-learning,10,620,1.0
Committed Q-learning,10,621,1.0
Committed Q-learning,10,622,1.0
Committed Q-learning,10,623,1.0
Committed Q-learning,10,624,1.0
Committed Q-learning,10,625,1.0
Committed Q-learning,10,626,1.0
Committed Q-learning,10,627,1.0
Committed Q-learning,10,628,1.0
Committed Q-learning,10,629,1.0
Committed Q-learning,10,630,1.0
Committed Q-learning,10,631,1.0
Committed Q-learning,10,632,1.0
Committed Q-learning,10,633,1.0
Committed Q-learning,10,634,1.0
Committed Q-learning,10,635,1.0
Committed Q-learning,10,636,1.0
Committed Q-learning,10,637,1.0
Committed Q-learning,10,638,1.0
Committed Q-learning,10,639,1.0
Committed Q-learning,10,640,1.0
Committed Q-learning,10,641,1.0
Committed Q-learning,10,642,1.0
Committed Q-learning,10,643,1.0
Committed Q-learning,10,644,1.0
Committed Q-learning,10,645,1.0
Committed Q-learning,10,646,1.0
Committed Q-learning,10,647,1.0
Committed Q-learning,10,648,1.0
Committed Q-learning,10,649,1.0
Committed Q-learning,10,650,1.0
Committed Q-learning,10,651,1.0
Committed Q-learning,10,652,1.0
Committed Q-learning,10,653,1.0
Committed Q-learning,10,654,1.0
Committed Q-learning,10,655,1.0
Committed Q-learning,10,656,1.0
Committed Q-learning,10,657,1.0
Committed Q-learning,10,658,1.0
Committed Q-learning,10,659,1.0
Committed Q-learning,10,660,1.0
Committed Q-learning,10,661,1.0
Committed Q-learning,10,662,1.0
Committed Q-learning,10,663,1.0
Committed Q-learning,10,664,1.0
Committed Q-learning,10,665,1.0
Committed Q-learning,10,666,1.0
Committed Q-learning,10,667,1.0
Committed Q-learning,10,668,1.0
Committed Q-learning,10,669,1.0
Committed Q-learning,10,670,1.0
Committed Q-learning,10,671,1.0
Committed Q-learning,10,672,1.0
Committed Q-learning,10,673,1.0
Committed Q-learning,10,674,1.0
Committed Q-learning,10,675,1.0
Committed Q-learning,10,676,1.0
Committed Q-learning,10,677,1.0
Committed Q-learning,10,678,1.0
Committed Q-learning,10,679,1.0
Committed Q-learning,10,680,1.0
Committed Q-learning,10,681,1.0
Committed Q-learning,10,682,1.0
Committed Q-learning,10,683,1.0
Committed Q-learning,10,684,1.0
Committed Q-learning,10,685,1.0
Committed Q-learning,10,686,1.0
Committed Q-learning,10,687,1.0
Committed Q-learning,10,688,1.0
Committed Q-learning,10,689,1.0
Committed Q-learning,10,690,1.0
Committed Q-learning,10,691,1.0
Committed Q-learning,10,692,1.0
Committed Q-learning,10,693,1.0
Committed Q-learning,10,694,1.0
Committed Q-learning,10,695,1.0
Committed Q-learning,10,696,1.0
Committed Q-learning,10,697,1.0
Committed Q-learning,10,698,1.0
Committed Q-learning,10,699,1.0
Committed Q-learning,10,700,1.0
Committed Q-learning,10,701,1.0
Committed Q-learning,10,702,1.0
Committed Q-learning,10,703,1.0
Committed Q-learning,10,704,1.0
Committed Q-learning,10,705,1.0
Committed Q-learning,10,706,1.0
Committed Q-learning,10,707,1.0
Committed Q-learning,10,708,1.0
Committed Q-learning,10,709,1.0
Committed Q-learning,10,710,1.0
Committed Q-learning,10,711,1.0
Committed Q-learning,10,712,1.0
Committed Q-learning,10,713,1.0
Committed Q-learning,10,714,1.0
Committed Q-learning,10,715,1.0
Committed Q-learning,10,716,1.0
Committed Q-learning,10,717,1.0
Committed Q-learning,10,718,1.0
Committed Q-learning,10,719,1.0
Committed Q-learning,10,720,1.0
Committed Q-learning,10,721,1.0
Committed Q-learning,10,722,1.0
Committed Q-learning,10,723,1.0
Committed Q-learning,10,724,1.0
Committed Q-learning,10,725,1.0
Committed Q-learning,10,726,1.0
Committed Q-learning,10,727,1.0
Committed Q-learning,10,728,1.0
Committed Q-learning,10,729,1.0
Committed Q-learning,10,730,1.0
Committed Q-learning,10,731,1.0
Committed Q-learning,10,732,1.0
Committed Q-learning,10,733,1.0
Committed Q-learning,10,734,1.0
Committed Q-learning,10,735,1.0
Committed Q-learning,10,736,1.0
Committed Q-learning,10,737,1.0
Committed Q-learning,10,738,1.0
Committed Q-learning,10,739,1.0
Committed Q-learning,10,740,1.0
Committed Q-learning,10,741,1.0
Committed Q-learning,10,742,1.0
Committed Q-learning,10,743,1.0
Committed Q-learning,10,744,1.0
Committed Q-learning,10,745,1.0
Committed Q-learning,10,746,1.0
Committed Q-learning,10,747,1.0
Committed Q-learning,10,748,1.0
Committed Q-learning,10,749,1.0
Committed Q-learning,10,750,1.0
Committed Q-learning,10,751,1.0
Committed Q-learning,10,752,1.0
Committed Q-learning,10,753,1.0
Committed Q-learning,10,754,1.0
Committed Q-learning,10,755,1.0
Committed Q-learning,10,756,1.0
Committed Q-learning,10,757,1.0
Committed Q-learning,10,758,1.0
Committed Q-learning,10,759,1.0
Committed Q-learning,10,760,1.0
Committed Q-learning,10,761,1.0
Committed Q-learning,10,762,1.0
Committed Q-learning,10,763,1.0
Committed Q-learning,10,764,1.0
Committed Q-learning,10,765,1.0
Committed Q-learning,10,766,1.0
Committed Q-learning,10,767,1.0
Committed Q-learning,10,768,1.0
Committed Q-learning,10,769,1.0
Committed Q-learning,10,770,1.0
Committed Q-learning,10,771,1.0
Committed Q-learning,10,772,1.0
Committed Q-learning,10,773,1.0
Committed Q-learning,10,774,1.0
Committed Q-learning,10,775,1.0
Committed Q-learning,10,776,1.0
Committed Q-learning,10,777,1.0
Committed Q-learning,10,778,1.0
Committed Q-learning,10,779,1.0
Committed Q-learning,10,780,1.0
Committed Q-learning,10,781,1.0
Committed Q-learning,10,782,1.0
Committed Q-learning,10,783,1.0
Committed Q-learning,10,784,1.0
Committed Q-learning,10,785,1.0
Committed Q-learning,10,786,1.0
Committed Q-learning,10,787,1.0
Committed Q-learning,10,788,1.0
Committed Q-learning,10,789,1.0
Committed Q-learning,10,790,1.0
Committed Q-learning,10,791,1.0
Committed Q-learning,10,792,1.0
Committed Q-learning,10,793,1.0
Committed Q-learning,10,794,1.0
Committed Q-learning,10,795,1.0
Committed Q-learning,10,796,1.0
Committed Q-learning,10,797,1.0
Committed Q-learning,10,798,1.0
Committed Q-learning,10,799,1.0
Committed Q-learning,10,800,1.0
Committed Q-learning,10,801,1.0
Committed Q-learning,10,802,1.0
Committed Q-learning,10,803,1.0
Committed Q-learning,10,804,1.0
Committed Q-learning,10,805,1.0
Committed Q-learning,10,806,1.0
Committed Q-learning,10,807,1.0
Committed Q-learning,10,808,1.0
Committed Q-learning,10,809,1.0
Committed Q-learning,10,810,1.0
Committed Q-learning,10,811,1.0
Committed Q-learning,10,812,1.0
Committed Q-learning,10,813,1.0
Committed Q-learning,10,814,1.0
Committed Q-learning,10,815,1.0
Committed Q-learning,10,816,1.0
Committed Q-learning,10,817,1.0
Committed Q-learning,10,818,1.0
Committed Q-learning,10,819,1.0
Committed Q-learning,10,820,1.0
Committed Q-learning,10,821,1.0
Committed Q-learning,10,822,1.0
Committed Q-learning,10,823,1.0
Committed Q-learning,10,824,1.0
Committed Q-learning,10,825,1.0
Committed Q-learning,10,826,1.0
Committed Q-learning,10,827,1.0
Committed Q-learning,10,828,1.0
Committed Q-learning,10,829,1.0
Committed Q-learning,10,830,1.0
Committed Q-learning,10,831,1.0
Committed Q-learning,10,832,1.0
Committed Q-learning,10,833,1.0
Committed Q-learning,10,834,1.0
Committed Q-learning,10,835,1.0
Committed Q-learning,10,836,1.0
Committed Q-learning,10,837,1.0
Committed Q-learning,10,838,1.0
Committed Q-learning,10,839,1.0
Committed Q-learning,10,840,1.0
Committed Q-learning,10,841,1.0
Committed Q-learning,10,842,1.0
Committed Q-learning,10,843,1.0
Committed Q-learning,10,844,1.0
Committed Q-learning,10,845,1.0
Committed Q-learning,10,846,1.0
Committed Q-learning,10,847,1.0
Committed Q-learning,10,848,1.0
Committed Q-learning,10,849,1.0
Committed Q-learning,10,850,1.0
Committed Q-learning,10,851,1.0
Committed Q-learning,10,852,1.0
Committed Q-learning,10,853,1.0
Committed Q-learning,10,854,1.0
Committed Q-learning,10,855,1.0
Committed Q-learning,10,856,1.0
Committed Q-learning,10,857,1.0
Committed Q-learning,10,858,1.0
Committed Q-learning,10,859,1.0
Committed Q-learning,10,860,1.0
Committed Q-learning,10,861,1.0
Committed Q-learning,10,862,1.0
Committed Q-learning,10,863,1.0
Committed Q-learning,10,864,1.0
Committed Q-learning,10,865,1.0
Committed Q-learning,10,866,1.0
Committed Q-learning,10,867,1.0
Committed Q-learning,10,868,1.0
Committed Q-learning,10,869,1.0
Committed Q-learning,10,870,1.0
Committed Q-learning,10,871,1.0
Committed Q-learning,10,872,1.0
Committed Q-learning,10,873,1.0
Committed Q-learning,10,874,1.0
Committed Q-learning,10,875,1.0
Committed Q-learning,10,876,1.0
Committed Q-learning,10,877,1.0
Committed Q-learning,10,878,1.0
Committed Q-learning,10,879,1.0
Committed Q-learning,10,880,1.0
Committed Q-learning,10,881,1.0
Committed Q-learning,10,882,1.0
Committed Q-learning,10,883,1.0
Committed Q-learning,10,884,1.0
Committed Q-learning,10,885,1.0
Committed Q-learning,10,886,1.0
Committed Q-learning,10,887,1.0
Committed Q-learning,10,888,1.0
Committed Q-learning,10,889,1.0
Committed Q-learning,10,890,1.0
Committed Q-learning,10,891,1.0
Committed Q-learning,10,892,1.0
Committed Q-learning,10,893,1.0
Committed Q-learning,10,894,1.0
Committed Q-learning,10,895,1.0
Committed Q-learning,10,896,1.0
Committed Q-learning,10,897,1.0
Committed Q-learning,10,898,1.0
Committed Q-learning,10,899,1.0
Committed Q-learning,10,900,1.0
Committed Q-learning,10,901,1.0
Committed Q-learning,10,902,1.0
Committed Q-learning,10,903,1.0
Committed Q-learning,10,904,1.0
Committed Q-learning,10,905,1.0
Committed Q-learning,10,906,1.0
Committed Q-learning,10,907,1.0
Committed Q-learning,10,908,1.0
Committed Q-learning,10,909,1.0
Committed Q-learning,10,910,1.0
Committed Q-learning,10,911,1.0
Committed Q-learning,10,912,1.0
Committed Q-learning,10,913,1.0
Committed Q-learning,10,914,1.0
Committed Q-learning,10,915,1.0
Committed Q-learning,10,916,1.0
Committed Q-learning,10,917,1.0
Committed Q-learning,10,918,1.0
Committed Q-learning,10,919,1.0
Committed Q-learning,10,920,1.0
Committed Q-learning,10,921,1.0
Committed Q-learning,10,922,1.0
Committed Q-learning,10,923,1.0
Committed Q-learning,10,924,1.0
Committed Q-learning,10,925,1.0
Committed Q-learning,10,926,1.0
Committed Q-learning,10,927,1.0
Committed Q-learning,10,928,1.0
Committed Q-learning,10,929,1.0
Committed Q-learning,10,930,1.0
Committed Q-learning,10,931,1.0
Committed Q-learning,10,932,1.0
Committed Q-learning,10,933,1.0
Committed Q-learning,10,934,1.0
Committed Q-learning,10,935,1.0
Committed Q-learning,10,936,1.0
Committed Q-learning,10,937,1.0
Committed Q-learning,10,938,1.0
Committed Q-learning,10,939,1.0
Committed Q-learning,10,940,1.0
Committed Q-learning,10,941,1.0
Committed Q-learning,10,942,1.0
Committed Q-learning,10,943,1.0
Committed Q-learning,10,944,1.0
Committed Q-learning,10,945,1.0
Committed Q-learning,10,946,1.0
Committed Q-learning,10,947,1.0
Committed Q-learning,10,948,1.0
Committed Q-learning,10,949,1.0
Committed Q-learning,10,950,1.0
Committed Q-learning,10,951,1.0
Committed Q-learning,10,952,1.0
Committed Q-learning,10,953,1.0
Committed Q-learning,10,954,1.0
Committed Q-learning,10,955,1.0
Committed Q-learning,10,956,1.0
Committed Q-learning,10,957,1.0
Committed Q-learning,10,958,1.0
Committed Q-learning,10,959,1.0
Committed Q-learning,10,960,1.0
Committed Q-learning,10,961,1.0
Committed Q-learning,10,962,1.0
Committed Q-learning,10,963,1.0
Committed Q-learning,10,964,1.0
Committed Q-learning,10,965,1.0
Committed Q-learning,10,966,1.0
Committed Q-learning,10,967,1.0
Committed Q-learning,10,968,1.0
Committed Q-learning,10,969,1.0
Committed Q-learning,10,970,1.0
Committed Q-learning,10,971,1.0
Committed Q-learning,10,972,1.0
Committed Q-learning,10,973,1.0
Committed Q-learning,10,974,1.0
Committed Q-learning,10,975,1.0
Committed Q-learning,10,976,1.0
Committed Q-learning,10,977,1.0
Committed Q-learning,10,978,1.0
Committed Q-learning,10,979,1.0
Committed Q-learning,10,980,1.0
Committed Q-learning,10,981,1.0
Committed Q-learning,10,982,1.0
Committed Q-learning,10,983,1.0
Committed Q-learning,10,984,1.0
Committed Q-learning,10,985,1.0
Committed Q-learning,10,986,1.0
Committed Q-learning,10,987,1.0
Committed Q-learning,10,988,1.0
Committed Q-learning,10,989,1.0
Committed Q-learning,10,990,1.0
Committed Q-learning,10,991,1.0
Committed Q-learning,10,992,1.0
Committed Q-learning,10,993,1.0
Committed Q-learning,10,994,1.0
Committed Q-learning,10,995,1.0
Committed Q-learning,10,996,1.0
Committed Q-learning,10,997,1.0
Committed Q-learning,10,998,1.0
Committed Q-learning,10,999,1.0
Committed Q-learning,10,1000,1.0
Committed Q-learning,20,1,0.24500000476837158
Committed Q-learning,20,2,0.2150000035762787
Committed Q-learning,20,3,0.1289999932050705
Committed Q-learning,20,4,0.07500000298023224
Committed Q-learning,20,5,0.04100000113248825
Committed Q-learning,20,6,0.032999999821186066
Committed Q-learning,20,7,0.014000000432133675
Committed Q-learning,20,8,0.014000000432133675
Committed Q-learning,20,9,0.01600000075995922
Committed Q-learning,20,10,0.017999999225139618
Committed Q-learning,20,11,0.023000000044703484
Committed Q-learning,20,12,0.027000000700354576
Committed Q-learning,20,13,0.02500000037252903
Committed Q-learning,20,14,0.024000000208616257
Committed Q-learning,20,15,0.020999999716877937
Committed Q-learning,20,16,0.017999999225139618
Committed Q-learning,20,17,0.024000000208616257
Committed Q-learning,20,18,0.020999999716877937
Committed Q-learning,20,19,0.014000000432133675
Committed Q-learning,20,20,0.013000000268220901
Committed Q-learning,20,21,0.07900000363588333
Committed Q-learning,20,22,0.2280000001192093
Committed Q-learning,20,23,0.35100001096725464
Committed Q-learning,20,24,0.4399999976158142
Committed Q-learning,20,25,0.49399998784065247
Committed Q-learning,20,26,0.5299999713897705
Committed Q-learning,20,27,0.5519999861717224
Committed Q-learning,20,28,0.5720000267028809
Committed Q-learning,20,29,0.5879999995231628
Committed Q-learning,20,30,0.6060000061988831
Committed Q-learning,20,31,0.628000020980835
Committed Q-learning,20,32,0.6439999938011169
Committed Q-learning,20,33,0.6729999780654907
Committed Q-learning,20,34,0.6470000147819519
Committed Q-learning,20,35,0.5540000200271606
Committed Q-learning,20,36,0.45399999618530273
Committed Q-learning,20,37,0.3779999911785126
Committed Q-learning,20,38,0.32100000977516174
Committed Q-learning,20,39,0.289000004529953
Committed Q-learning,20,40,0.2680000066757202
Committed Q-learning,20,41,0.25699999928474426
Committed Q-learning,20,42,0.3100000023841858
Committed Q-learning,20,43,0.4490000009536743
Committed Q-learning,20,44,0.5659999847412109
Committed Q-learning,20,45,0.6639999747276306
Committed Q-learning,20,46,0.7139999866485596
Committed Q-learning,20,47,0.7419999837875366
Committed Q-learning,20,48,0.7549999952316284
Committed Q-learning,20,49,0.7670000195503235
Committed Q-learning,20,50,0.7689999938011169
Committed Q-learning,20,51,0.7689999938011169
Committed Q-learning,20,52,0.7799999713897705
Committed Q-learning,20,53,0.777999997138977
Committed Q-learning,20,54,0.8019999861717224
Committed Q-learning,20,55,0.8100000023841858
Committed Q-learning,20,56,0.828000009059906
Committed Q-learning,20,57,0.8360000252723694
Committed Q-learning,20,58,0.843999981880188
Committed Q-learning,20,59,0.8100000023841858
Committed Q-learning,20,60,0.6990000009536743
Committed Q-learning,20,61,0.5820000171661377
Committed Q-learning,20,62,0.48399999737739563
Committed Q-learning,20,63,0.4749999940395355
Committed Q-learning,20,64,0.5609999895095825
Committed Q-learning,20,65,0.6669999957084656
Committed Q-learning,20,66,0.7559999823570251
Committed Q-learning,20,67,0.8090000152587891
Committed Q-learning,20,68,0.8460000157356262
Committed Q-learning,20,69,0.8700000047683716
Committed Q-learning,20,70,0.8610000014305115
Committed Q-learning,20,71,0.8579999804496765
Committed Q-learning,20,72,0.8550000190734863
Committed Q-learning,20,73,0.8650000095367432
Committed Q-learning,20,74,0.8650000095367432
Committed Q-learning,20,75,0.8809999823570251
Committed Q-learning,20,76,0.8870000243186951
Committed Q-learning,20,77,0.8989999890327454
Committed Q-learning,20,78,0.9010000228881836
Committed Q-learning,20,79,0.9100000262260437
Committed Q-learning,20,80,0.9179999828338623
Committed Q-learning,20,81,0.9200000166893005
Committed Q-learning,20,82,0.8980000019073486
Committed Q-learning,20,83,0.8180000185966492
Committed Q-learning,20,84,0.7369999885559082
Committed Q-learning,20,85,0.7670000195503235
Committed Q-learning,20,86,0.8090000152587891
Committed Q-learning,20,87,0.8569999933242798
Committed Q-learning,20,88,0.8930000066757202
Committed Q-learning,20,89,0.9120000004768372
Committed Q-learning,20,90,0.9350000023841858
Committed Q-learning,20,91,0.9480000138282776
Committed Q-learning,20,92,0.9399999976158142
Committed Q-learning,20,93,0.9369999766349792
Committed Q-learning,20,94,0.9319999814033508
Committed Q-learning,20,95,0.9259999990463257
Committed Q-learning,20,96,0.9319999814033508
Committed Q-learning,20,97,0.9369999766349792
Committed Q-learning,20,98,0.9470000267028809
Committed Q-learning,20,99,0.949999988079071
Committed Q-learning,20,100,0.953000009059906
Committed Q-learning,20,101,0.9559999704360962
Committed Q-learning,20,102,0.9599999785423279
Committed Q-learning,20,103,0.9620000123977661
Committed Q-learning,20,104,0.9649999737739563
Committed Q-learning,20,105,0.9610000252723694
Committed Q-learning,20,106,0.9559999704360962
Committed Q-learning,20,107,0.972000002861023
Committed Q-learning,20,108,0.9760000109672546
Committed Q-learning,20,109,0.9850000143051147
Committed Q-learning,20,110,0.9890000224113464
Committed Q-learning,20,111,0.9900000095367432
Committed Q-learning,20,112,0.9890000224113464
Committed Q-learning,20,113,0.9879999756813049
Committed Q-learning,20,114,0.9879999756813049
Committed Q-learning,20,115,0.9879999756813049
Committed Q-learning,20,116,0.9869999885559082
Committed Q-learning,20,117,0.9929999709129333
Committed Q-learning,20,118,0.9869999885559082
Committed Q-learning,20,119,0.9909999966621399
Committed Q-learning,20,120,0.9919999837875366
Committed Q-learning,20,121,0.996999979019165
Committed Q-learning,20,122,0.996999979019165
Committed Q-learning,20,123,0.996999979019165
Committed Q-learning,20,124,0.996999979019165
Committed Q-learning,20,125,0.9959999918937683
Committed Q-learning,20,126,0.996999979019165
Committed Q-learning,20,127,0.996999979019165
Committed Q-learning,20,128,0.996999979019165
Committed Q-learning,20,129,0.9940000176429749
Committed Q-learning,20,130,0.9990000128746033
Committed Q-learning,20,131,0.9990000128746033
Committed Q-learning,20,132,0.9990000128746033
Committed Q-learning,20,133,1.0
Committed Q-learning,20,134,0.9990000128746033
Committed Q-learning,20,135,0.9959999918937683
Committed Q-learning,20,136,0.9980000257492065
Committed Q-learning,20,137,0.9980000257492065
Committed Q-learning,20,138,0.996999979019165
Committed Q-learning,20,139,0.9990000128746033
Committed Q-learning,20,140,1.0
Committed Q-learning,20,141,0.996999979019165
Committed Q-learning,20,142,0.9990000128746033
Committed Q-learning,20,143,1.0
Committed Q-learning,20,144,1.0
Committed Q-learning,20,145,1.0
Committed Q-learning,20,146,1.0
Committed Q-learning,20,147,1.0
Committed Q-learning,20,148,1.0
Committed Q-learning,20,149,1.0
Committed Q-learning,20,150,1.0
Committed Q-learning,20,151,1.0
Committed Q-learning,20,152,1.0
Committed Q-learning,20,153,1.0
Committed Q-learning,20,154,1.0
Committed Q-learning,20,155,1.0
Committed Q-learning,20,156,1.0
Committed Q-learning,20,157,1.0
Committed Q-learning,20,158,0.9990000128746033
Committed Q-learning,20,159,1.0
Committed Q-learning,20,160,1.0
Committed Q-learning,20,161,1.0
Committed Q-learning,20,162,1.0
Committed Q-learning,20,163,1.0
Committed Q-learning,20,164,1.0
Committed Q-learning,20,165,1.0
Committed Q-learning,20,166,1.0
Committed Q-learning,20,167,1.0
Committed Q-learning,20,168,1.0
Committed Q-learning,20,169,1.0
Committed Q-learning,20,170,1.0
Committed Q-learning,20,171,1.0
Committed Q-learning,20,172,1.0
Committed Q-learning,20,173,1.0
Committed Q-learning,20,174,1.0
Committed Q-learning,20,175,1.0
Committed Q-learning,20,176,1.0
Committed Q-learning,20,177,1.0
Committed Q-learning,20,178,1.0
Committed Q-learning,20,179,1.0
Committed Q-learning,20,180,1.0
Committed Q-learning,20,181,1.0
Committed Q-learning,20,182,1.0
Committed Q-learning,20,183,1.0
Committed Q-learning,20,184,1.0
Committed Q-learning,20,185,1.0
Committed Q-learning,20,186,1.0
Committed Q-learning,20,187,1.0
Committed Q-learning,20,188,1.0
Committed Q-learning,20,189,1.0
Committed Q-learning,20,190,1.0
Committed Q-learning,20,191,1.0
Committed Q-learning,20,192,1.0
Committed Q-learning,20,193,1.0
Committed Q-learning,20,194,1.0
Committed Q-learning,20,195,1.0
Committed Q-learning,20,196,1.0
Committed Q-learning,20,197,1.0
Committed Q-learning,20,198,1.0
Committed Q-learning,20,199,1.0
Committed Q-learning,20,200,1.0
Committed Q-learning,20,201,1.0
Committed Q-learning,20,202,1.0
Committed Q-learning,20,203,1.0
Committed Q-learning,20,204,1.0
Committed Q-learning,20,205,1.0
Committed Q-learning,20,206,1.0
Committed Q-learning,20,207,1.0
Committed Q-learning,20,208,1.0
Committed Q-learning,20,209,1.0
Committed Q-learning,20,210,1.0
Committed Q-learning,20,211,1.0
Committed Q-learning,20,212,1.0
Committed Q-learning,20,213,1.0
Committed Q-learning,20,214,1.0
Committed Q-learning,20,215,1.0
Committed Q-learning,20,216,1.0
Committed Q-learning,20,217,1.0
Committed Q-learning,20,218,1.0
Committed Q-learning,20,219,1.0
Committed Q-learning,20,220,1.0
Committed Q-learning,20,221,1.0
Committed Q-learning,20,222,1.0
Committed Q-learning,20,223,1.0
Committed Q-learning,20,224,1.0
Committed Q-learning,20,225,1.0
Committed Q-learning,20,226,1.0
Committed Q-learning,20,227,1.0
Committed Q-learning,20,228,1.0
Committed Q-learning,20,229,1.0
Committed Q-learning,20,230,1.0
Committed Q-learning,20,231,1.0
Committed Q-learning,20,232,1.0
Committed Q-learning,20,233,1.0
Committed Q-learning,20,234,1.0
Committed Q-learning,20,235,1.0
Committed Q-learning,20,236,1.0
Committed Q-learning,20,237,1.0
Committed Q-learning,20,238,1.0
Committed Q-learning,20,239,1.0
Committed Q-learning,20,240,1.0
Committed Q-learning,20,241,1.0
Committed Q-learning,20,242,1.0
Committed Q-learning,20,243,1.0
Committed Q-learning,20,244,1.0
Committed Q-learning,20,245,1.0
Committed Q-learning,20,246,1.0
Committed Q-learning,20,247,1.0
Committed Q-learning,20,248,1.0
Committed Q-learning,20,249,1.0
Committed Q-learning,20,250,1.0
Committed Q-learning,20,251,1.0
Committed Q-learning,20,252,1.0
Committed Q-learning,20,253,1.0
Committed Q-learning,20,254,1.0
Committed Q-learning,20,255,1.0
Committed Q-learning,20,256,1.0
Committed Q-learning,20,257,1.0
Committed Q-learning,20,258,1.0
Committed Q-learning,20,259,1.0
Committed Q-learning,20,260,1.0
Committed Q-learning,20,261,1.0
Committed Q-learning,20,262,1.0
Committed Q-learning,20,263,1.0
Committed Q-learning,20,264,1.0
Committed Q-learning,20,265,1.0
Committed Q-learning,20,266,1.0
Committed Q-learning,20,267,1.0
Committed Q-learning,20,268,1.0
Committed Q-learning,20,269,1.0
Committed Q-learning,20,270,1.0
Committed Q-learning,20,271,1.0
Committed Q-learning,20,272,1.0
Committed Q-learning,20,273,1.0
Committed Q-learning,20,274,1.0
Committed Q-learning,20,275,1.0
Committed Q-learning,20,276,1.0
Committed Q-learning,20,277,1.0
Committed Q-learning,20,278,1.0
Committed Q-learning,20,279,1.0
Committed Q-learning,20,280,1.0
Committed Q-learning,20,281,1.0
Committed Q-learning,20,282,1.0
Committed Q-learning,20,283,1.0
Committed Q-learning,20,284,1.0
Committed Q-learning,20,285,1.0
Committed Q-learning,20,286,1.0
Committed Q-learning,20,287,1.0
Committed Q-learning,20,288,1.0
Committed Q-learning,20,289,1.0
Committed Q-learning,20,290,1.0
Committed Q-learning,20,291,1.0
Committed Q-learning,20,292,1.0
Committed Q-learning,20,293,1.0
Committed Q-learning,20,294,1.0
Committed Q-learning,20,295,1.0
Committed Q-learning,20,296,1.0
Committed Q-learning,20,297,1.0
Committed Q-learning,20,298,1.0
Committed Q-learning,20,299,1.0
Committed Q-learning,20,300,1.0
Committed Q-learning,20,301,1.0
Committed Q-learning,20,302,1.0
Committed Q-learning,20,303,1.0
Committed Q-learning,20,304,1.0
Committed Q-learning,20,305,1.0
Committed Q-learning,20,306,1.0
Committed Q-learning,20,307,1.0
Committed Q-learning,20,308,1.0
Committed Q-learning,20,309,1.0
Committed Q-learning,20,310,1.0
Committed Q-learning,20,311,1.0
Committed Q-learning,20,312,1.0
Committed Q-learning,20,313,1.0
Committed Q-learning,20,314,1.0
Committed Q-learning,20,315,1.0
Committed Q-learning,20,316,1.0
Committed Q-learning,20,317,1.0
Committed Q-learning,20,318,1.0
Committed Q-learning,20,319,1.0
Committed Q-learning,20,320,1.0
Committed Q-learning,20,321,1.0
Committed Q-learning,20,322,1.0
Committed Q-learning,20,323,1.0
Committed Q-learning,20,324,1.0
Committed Q-learning,20,325,1.0
Committed Q-learning,20,326,1.0
Committed Q-learning,20,327,1.0
Committed Q-learning,20,328,1.0
Committed Q-learning,20,329,1.0
Committed Q-learning,20,330,1.0
Committed Q-learning,20,331,1.0
Committed Q-learning,20,332,1.0
Committed Q-learning,20,333,1.0
Committed Q-learning,20,334,1.0
Committed Q-learning,20,335,1.0
Committed Q-learning,20,336,1.0
Committed Q-learning,20,337,1.0
Committed Q-learning,20,338,1.0
Committed Q-learning,20,339,1.0
Committed Q-learning,20,340,1.0
Committed Q-learning,20,341,1.0
Committed Q-learning,20,342,1.0
Committed Q-learning,20,343,1.0
Committed Q-learning,20,344,1.0
Committed Q-learning,20,345,1.0
Committed Q-learning,20,346,1.0
Committed Q-learning,20,347,1.0
Committed Q-learning,20,348,1.0
Committed Q-learning,20,349,1.0
Committed Q-learning,20,350,1.0
Committed Q-learning,20,351,1.0
Committed Q-learning,20,352,1.0
Committed Q-learning,20,353,1.0
Committed Q-learning,20,354,1.0
Committed Q-learning,20,355,1.0
Committed Q-learning,20,356,1.0
Committed Q-learning,20,357,1.0
Committed Q-learning,20,358,1.0
Committed Q-learning,20,359,1.0
Committed Q-learning,20,360,1.0
Committed Q-learning,20,361,1.0
Committed Q-learning,20,362,1.0
Committed Q-learning,20,363,1.0
Committed Q-learning,20,364,1.0
Committed Q-learning,20,365,1.0
Committed Q-learning,20,366,1.0
Committed Q-learning,20,367,1.0
Committed Q-learning,20,368,1.0
Committed Q-learning,20,369,1.0
Committed Q-learning,20,370,1.0
Committed Q-learning,20,371,1.0
Committed Q-learning,20,372,1.0
Committed Q-learning,20,373,1.0
Committed Q-learning,20,374,1.0
Committed Q-learning,20,375,1.0
Committed Q-learning,20,376,1.0
Committed Q-learning,20,377,1.0
Committed Q-learning,20,378,1.0
Committed Q-learning,20,379,1.0
Committed Q-learning,20,380,1.0
Committed Q-learning,20,381,1.0
Committed Q-learning,20,382,1.0
Committed Q-learning,20,383,1.0
Committed Q-learning,20,384,1.0
Committed Q-learning,20,385,1.0
Committed Q-learning,20,386,1.0
Committed Q-learning,20,387,1.0
Committed Q-learning,20,388,1.0
Committed Q-learning,20,389,1.0
Committed Q-learning,20,390,1.0
Committed Q-learning,20,391,1.0
Committed Q-learning,20,392,1.0
Committed Q-learning,20,393,1.0
Committed Q-learning,20,394,1.0
Committed Q-learning,20,395,1.0
Committed Q-learning,20,396,1.0
Committed Q-learning,20,397,1.0
Committed Q-learning,20,398,1.0
Committed Q-learning,20,399,1.0
Committed Q-learning,20,400,1.0
Committed Q-learning,20,401,1.0
Committed Q-learning,20,402,1.0
Committed Q-learning,20,403,1.0
Committed Q-learning,20,404,1.0
Committed Q-learning,20,405,1.0
Committed Q-learning,20,406,1.0
Committed Q-learning,20,407,1.0
Committed Q-learning,20,408,1.0
Committed Q-learning,20,409,1.0
Committed Q-learning,20,410,1.0
Committed Q-learning,20,411,1.0
Committed Q-learning,20,412,1.0
Committed Q-learning,20,413,1.0
Committed Q-learning,20,414,1.0
Committed Q-learning,20,415,1.0
Committed Q-learning,20,416,1.0
Committed Q-learning,20,417,1.0
Committed Q-learning,20,418,1.0
Committed Q-learning,20,419,1.0
Committed Q-learning,20,420,1.0
Committed Q-learning,20,421,1.0
Committed Q-learning,20,422,1.0
Committed Q-learning,20,423,1.0
Committed Q-learning,20,424,1.0
Committed Q-learning,20,425,1.0
Committed Q-learning,20,426,1.0
Committed Q-learning,20,427,1.0
Committed Q-learning,20,428,1.0
Committed Q-learning,20,429,1.0
Committed Q-learning,20,430,1.0
Committed Q-learning,20,431,1.0
Committed Q-learning,20,432,1.0
Committed Q-learning,20,433,1.0
Committed Q-learning,20,434,1.0
Committed Q-learning,20,435,1.0
Committed Q-learning,20,436,1.0
Committed Q-learning,20,437,1.0
Committed Q-learning,20,438,1.0
Committed Q-learning,20,439,1.0
Committed Q-learning,20,440,1.0
Committed Q-learning,20,441,1.0
Committed Q-learning,20,442,1.0
Committed Q-learning,20,443,1.0
Committed Q-learning,20,444,1.0
Committed Q-learning,20,445,1.0
Committed Q-learning,20,446,1.0
Committed Q-learning,20,447,1.0
Committed Q-learning,20,448,1.0
Committed Q-learning,20,449,1.0
Committed Q-learning,20,450,1.0
Committed Q-learning,20,451,1.0
Committed Q-learning,20,452,1.0
Committed Q-learning,20,453,1.0
Committed Q-learning,20,454,1.0
Committed Q-learning,20,455,1.0
Committed Q-learning,20,456,1.0
Committed Q-learning,20,457,1.0
Committed Q-learning,20,458,1.0
Committed Q-learning,20,459,1.0
Committed Q-learning,20,460,1.0
Committed Q-learning,20,461,1.0
Committed Q-learning,20,462,1.0
Committed Q-learning,20,463,1.0
Committed Q-learning,20,464,1.0
Committed Q-learning,20,465,1.0
Committed Q-learning,20,466,1.0
Committed Q-learning,20,467,1.0
Committed Q-learning,20,468,1.0
Committed Q-learning,20,469,1.0
Committed Q-learning,20,470,1.0
Committed Q-learning,20,471,1.0
Committed Q-learning,20,472,1.0
Committed Q-learning,20,473,1.0
Committed Q-learning,20,474,1.0
Committed Q-learning,20,475,1.0
Committed Q-learning,20,476,1.0
Committed Q-learning,20,477,1.0
Committed Q-learning,20,478,1.0
Committed Q-learning,20,479,1.0
Committed Q-learning,20,480,1.0
Committed Q-learning,20,481,1.0
Committed Q-learning,20,482,1.0
Committed Q-learning,20,483,1.0
Committed Q-learning,20,484,1.0
Committed Q-learning,20,485,1.0
Committed Q-learning,20,486,1.0
Committed Q-learning,20,487,1.0
Committed Q-learning,20,488,1.0
Committed Q-learning,20,489,1.0
Committed Q-learning,20,490,1.0
Committed Q-learning,20,491,1.0
Committed Q-learning,20,492,1.0
Committed Q-learning,20,493,1.0
Committed Q-learning,20,494,1.0
Committed Q-learning,20,495,1.0
Committed Q-learning,20,496,1.0
Committed Q-learning,20,497,1.0
Committed Q-learning,20,498,1.0
Committed Q-learning,20,499,1.0
Committed Q-learning,20,500,1.0
Committed Q-learning,20,501,1.0
Committed Q-learning,20,502,1.0
Committed Q-learning,20,503,1.0
Committed Q-learning,20,504,1.0
Committed Q-learning,20,505,1.0
Committed Q-learning,20,506,1.0
Committed Q-learning,20,507,1.0
Committed Q-learning,20,508,1.0
Committed Q-learning,20,509,1.0
Committed Q-learning,20,510,1.0
Committed Q-learning,20,511,1.0
Committed Q-learning,20,512,1.0
Committed Q-learning,20,513,1.0
Committed Q-learning,20,514,1.0
Committed Q-learning,20,515,1.0
Committed Q-learning,20,516,1.0
Committed Q-learning,20,517,1.0
Committed Q-learning,20,518,1.0
Committed Q-learning,20,519,1.0
Committed Q-learning,20,520,1.0
Committed Q-learning,20,521,1.0
Committed Q-learning,20,522,1.0
Committed Q-learning,20,523,1.0
Committed Q-learning,20,524,1.0
Committed Q-learning,20,525,1.0
Committed Q-learning,20,526,1.0
Committed Q-learning,20,527,1.0
Committed Q-learning,20,528,1.0
Committed Q-learning,20,529,1.0
Committed Q-learning,20,530,1.0
Committed Q-learning,20,531,1.0
Committed Q-learning,20,532,1.0
Committed Q-learning,20,533,1.0
Committed Q-learning,20,534,1.0
Committed Q-learning,20,535,1.0
Committed Q-learning,20,536,1.0
Committed Q-learning,20,537,1.0
Committed Q-learning,20,538,1.0
Committed Q-learning,20,539,1.0
Committed Q-learning,20,540,1.0
Committed Q-learning,20,541,1.0
Committed Q-learning,20,542,1.0
Committed Q-learning,20,543,1.0
Committed Q-learning,20,544,1.0
Committed Q-learning,20,545,1.0
Committed Q-learning,20,546,1.0
Committed Q-learning,20,547,1.0
Committed Q-learning,20,548,1.0
Committed Q-learning,20,549,1.0
Committed Q-learning,20,550,1.0
Committed Q-learning,20,551,1.0
Committed Q-learning,20,552,1.0
Committed Q-learning,20,553,1.0
Committed Q-learning,20,554,1.0
Committed Q-learning,20,555,1.0
Committed Q-learning,20,556,1.0
Committed Q-learning,20,557,1.0
Committed Q-learning,20,558,1.0
Committed Q-learning,20,559,1.0
Committed Q-learning,20,560,1.0
Committed Q-learning,20,561,1.0
Committed Q-learning,20,562,1.0
Committed Q-learning,20,563,1.0
Committed Q-learning,20,564,1.0
Committed Q-learning,20,565,1.0
Committed Q-learning,20,566,1.0
Committed Q-learning,20,567,1.0
Committed Q-learning,20,568,1.0
Committed Q-learning,20,569,1.0
Committed Q-learning,20,570,1.0
Committed Q-learning,20,571,1.0
Committed Q-learning,20,572,1.0
Committed Q-learning,20,573,1.0
Committed Q-learning,20,574,1.0
Committed Q-learning,20,575,1.0
Committed Q-learning,20,576,1.0
Committed Q-learning,20,577,1.0
Committed Q-learning,20,578,1.0
Committed Q-learning,20,579,1.0
Committed Q-learning,20,580,1.0
Committed Q-learning,20,581,1.0
Committed Q-learning,20,582,1.0
Committed Q-learning,20,583,1.0
Committed Q-learning,20,584,1.0
Committed Q-learning,20,585,1.0
Committed Q-learning,20,586,1.0
Committed Q-learning,20,587,1.0
Committed Q-learning,20,588,1.0
Committed Q-learning,20,589,1.0
Committed Q-learning,20,590,1.0
Committed Q-learning,20,591,1.0
Committed Q-learning,20,592,1.0
Committed Q-learning,20,593,1.0
Committed Q-learning,20,594,1.0
Committed Q-learning,20,595,1.0
Committed Q-learning,20,596,1.0
Committed Q-learning,20,597,1.0
Committed Q-learning,20,598,1.0
Committed Q-learning,20,599,1.0
Committed Q-learning,20,600,1.0
Committed Q-learning,20,601,1.0
Committed Q-learning,20,602,1.0
Committed Q-learning,20,603,1.0
Committed Q-learning,20,604,1.0
Committed Q-learning,20,605,1.0
Committed Q-learning,20,606,1.0
Committed Q-learning,20,607,1.0
Committed Q-learning,20,608,1.0
Committed Q-learning,20,609,1.0
Committed Q-learning,20,610,1.0
Committed Q-learning,20,611,1.0
Committed Q-learning,20,612,1.0
Committed Q-learning,20,613,1.0
Committed Q-learning,20,614,1.0
Committed Q-learning,20,615,1.0
Committed Q-learning,20,616,1.0
Committed Q-learning,20,617,1.0
Committed Q-learning,20,618,1.0
Committed Q-learning,20,619,1.0
Committed Q-learning,20,620,1.0
Committed Q-learning,20,621,1.0
Committed Q-learning,20,622,1.0
Committed Q-learning,20,623,1.0
Committed Q-learning,20,624,1.0
Committed Q-learning,20,625,1.0
Committed Q-learning,20,626,1.0
Committed Q-learning,20,627,1.0
Committed Q-learning,20,628,1.0
Committed Q-learning,20,629,1.0
Committed Q-learning,20,630,1.0
Committed Q-learning,20,631,1.0
Committed Q-learning,20,632,1.0
Committed Q-learning,20,633,1.0
Committed Q-learning,20,634,1.0
Committed Q-learning,20,635,1.0
Committed Q-learning,20,636,1.0
Committed Q-learning,20,637,1.0
Committed Q-learning,20,638,1.0
Committed Q-learning,20,639,1.0
Committed Q-learning,20,640,1.0
Committed Q-learning,20,641,1.0
Committed Q-learning,20,642,1.0
Committed Q-learning,20,643,1.0
Committed Q-learning,20,644,1.0
Committed Q-learning,20,645,1.0
Committed Q-learning,20,646,1.0
Committed Q-learning,20,647,1.0
Committed Q-learning,20,648,1.0
Committed Q-learning,20,649,1.0
Committed Q-learning,20,650,1.0
Committed Q-learning,20,651,1.0
Committed Q-learning,20,652,1.0
Committed Q-learning,20,653,1.0
Committed Q-learning,20,654,1.0
Committed Q-learning,20,655,1.0
Committed Q-learning,20,656,1.0
Committed Q-learning,20,657,1.0
Committed Q-learning,20,658,1.0
Committed Q-learning,20,659,1.0
Committed Q-learning,20,660,1.0
Committed Q-learning,20,661,1.0
Committed Q-learning,20,662,1.0
Committed Q-learning,20,663,1.0
Committed Q-learning,20,664,1.0
Committed Q-learning,20,665,1.0
Committed Q-learning,20,666,1.0
Committed Q-learning,20,667,1.0
Committed Q-learning,20,668,1.0
Committed Q-learning,20,669,1.0
Committed Q-learning,20,670,1.0
Committed Q-learning,20,671,1.0
Committed Q-learning,20,672,1.0
Committed Q-learning,20,673,1.0
Committed Q-learning,20,674,1.0
Committed Q-learning,20,675,1.0
Committed Q-learning,20,676,1.0
Committed Q-learning,20,677,1.0
Committed Q-learning,20,678,1.0
Committed Q-learning,20,679,1.0
Committed Q-learning,20,680,1.0
Committed Q-learning,20,681,1.0
Committed Q-learning,20,682,1.0
Committed Q-learning,20,683,1.0
Committed Q-learning,20,684,1.0
Committed Q-learning,20,685,1.0
Committed Q-learning,20,686,1.0
Committed Q-learning,20,687,1.0
Committed Q-learning,20,688,1.0
Committed Q-learning,20,689,1.0
Committed Q-learning,20,690,1.0
Committed Q-learning,20,691,1.0
Committed Q-learning,20,692,1.0
Committed Q-learning,20,693,1.0
Committed Q-learning,20,694,1.0
Committed Q-learning,20,695,1.0
Committed Q-learning,20,696,1.0
Committed Q-learning,20,697,1.0
Committed Q-learning,20,698,1.0
Committed Q-learning,20,699,1.0
Committed Q-learning,20,700,1.0
Committed Q-learning,20,701,1.0
Committed Q-learning,20,702,1.0
Committed Q-learning,20,703,1.0
Committed Q-learning,20,704,1.0
Committed Q-learning,20,705,1.0
Committed Q-learning,20,706,1.0
Committed Q-learning,20,707,1.0
Committed Q-learning,20,708,1.0
Committed Q-learning,20,709,1.0
Committed Q-learning,20,710,1.0
Committed Q-learning,20,711,1.0
Committed Q-learning,20,712,1.0
Committed Q-learning,20,713,1.0
Committed Q-learning,20,714,1.0
Committed Q-learning,20,715,1.0
Committed Q-learning,20,716,1.0
Committed Q-learning,20,717,1.0
Committed Q-learning,20,718,1.0
Committed Q-learning,20,719,1.0
Committed Q-learning,20,720,1.0
Committed Q-learning,20,721,1.0
Committed Q-learning,20,722,1.0
Committed Q-learning,20,723,1.0
Committed Q-learning,20,724,1.0
Committed Q-learning,20,725,1.0
Committed Q-learning,20,726,1.0
Committed Q-learning,20,727,1.0
Committed Q-learning,20,728,1.0
Committed Q-learning,20,729,1.0
Committed Q-learning,20,730,1.0
Committed Q-learning,20,731,1.0
Committed Q-learning,20,732,1.0
Committed Q-learning,20,733,1.0
Committed Q-learning,20,734,1.0
Committed Q-learning,20,735,1.0
Committed Q-learning,20,736,1.0
Committed Q-learning,20,737,1.0
Committed Q-learning,20,738,1.0
Committed Q-learning,20,739,1.0
Committed Q-learning,20,740,1.0
Committed Q-learning,20,741,1.0
Committed Q-learning,20,742,1.0
Committed Q-learning,20,743,1.0
Committed Q-learning,20,744,1.0
Committed Q-learning,20,745,1.0
Committed Q-learning,20,746,1.0
Committed Q-learning,20,747,1.0
Committed Q-learning,20,748,1.0
Committed Q-learning,20,749,1.0
Committed Q-learning,20,750,1.0
Committed Q-learning,20,751,1.0
Committed Q-learning,20,752,1.0
Committed Q-learning,20,753,1.0
Committed Q-learning,20,754,1.0
Committed Q-learning,20,755,1.0
Committed Q-learning,20,756,1.0
Committed Q-learning,20,757,1.0
Committed Q-learning,20,758,1.0
Committed Q-learning,20,759,1.0
Committed Q-learning,20,760,1.0
Committed Q-learning,20,761,1.0
Committed Q-learning,20,762,1.0
Committed Q-learning,20,763,1.0
Committed Q-learning,20,764,1.0
Committed Q-learning,20,765,1.0
Committed Q-learning,20,766,1.0
Committed Q-learning,20,767,1.0
Committed Q-learning,20,768,1.0
Committed Q-learning,20,769,1.0
Committed Q-learning,20,770,1.0
Committed Q-learning,20,771,1.0
Committed Q-learning,20,772,1.0
Committed Q-learning,20,773,1.0
Committed Q-learning,20,774,1.0
Committed Q-learning,20,775,1.0
Committed Q-learning,20,776,1.0
Committed Q-learning,20,777,1.0
Committed Q-learning,20,778,1.0
Committed Q-learning,20,779,1.0
Committed Q-learning,20,780,1.0
Committed Q-learning,20,781,1.0
Committed Q-learning,20,782,1.0
Committed Q-learning,20,783,1.0
Committed Q-learning,20,784,1.0
Committed Q-learning,20,785,1.0
Committed Q-learning,20,786,1.0
Committed Q-learning,20,787,1.0
Committed Q-learning,20,788,1.0
Committed Q-learning,20,789,1.0
Committed Q-learning,20,790,1.0
Committed Q-learning,20,791,1.0
Committed Q-learning,20,792,1.0
Committed Q-learning,20,793,1.0
Committed Q-learning,20,794,1.0
Committed Q-learning,20,795,1.0
Committed Q-learning,20,796,1.0
Committed Q-learning,20,797,1.0
Committed Q-learning,20,798,1.0
Committed Q-learning,20,799,1.0
Committed Q-learning,20,800,1.0
Committed Q-learning,20,801,1.0
Committed Q-learning,20,802,1.0
Committed Q-learning,20,803,1.0
Committed Q-learning,20,804,1.0
Committed Q-learning,20,805,1.0
Committed Q-learning,20,806,1.0
Committed Q-learning,20,807,1.0
Committed Q-learning,20,808,1.0
Committed Q-learning,20,809,1.0
Committed Q-learning,20,810,1.0
Committed Q-learning,20,811,1.0
Committed Q-learning,20,812,1.0
Committed Q-learning,20,813,1.0
Committed Q-learning,20,814,1.0
Committed Q-learning,20,815,1.0
Committed Q-learning,20,816,1.0
Committed Q-learning,20,817,1.0
Committed Q-learning,20,818,1.0
Committed Q-learning,20,819,1.0
Committed Q-learning,20,820,1.0
Committed Q-learning,20,821,1.0
Committed Q-learning,20,822,1.0
Committed Q-learning,20,823,1.0
Committed Q-learning,20,824,1.0
Committed Q-learning,20,825,1.0
Committed Q-learning,20,826,1.0
Committed Q-learning,20,827,1.0
Committed Q-learning,20,828,1.0
Committed Q-learning,20,829,1.0
Committed Q-learning,20,830,1.0
Committed Q-learning,20,831,1.0
Committed Q-learning,20,832,1.0
Committed Q-learning,20,833,1.0
Committed Q-learning,20,834,1.0
Committed Q-learning,20,835,1.0
Committed Q-learning,20,836,1.0
Committed Q-learning,20,837,1.0
Committed Q-learning,20,838,1.0
Committed Q-learning,20,839,1.0
Committed Q-learning,20,840,1.0
Committed Q-learning,20,841,1.0
Committed Q-learning,20,842,1.0
Committed Q-learning,20,843,1.0
Committed Q-learning,20,844,1.0
Committed Q-learning,20,845,1.0
Committed Q-learning,20,846,1.0
Committed Q-learning,20,847,1.0
Committed Q-learning,20,848,1.0
Committed Q-learning,20,849,1.0
Committed Q-learning,20,850,1.0
Committed Q-learning,20,851,1.0
Committed Q-learning,20,852,1.0
Committed Q-learning,20,853,1.0
Committed Q-learning,20,854,1.0
Committed Q-learning,20,855,1.0
Committed Q-learning,20,856,1.0
Committed Q-learning,20,857,1.0
Committed Q-learning,20,858,1.0
Committed Q-learning,20,859,1.0
Committed Q-learning,20,860,1.0
Committed Q-learning,20,861,1.0
Committed Q-learning,20,862,1.0
Committed Q-learning,20,863,1.0
Committed Q-learning,20,864,1.0
Committed Q-learning,20,865,1.0
Committed Q-learning,20,866,1.0
Committed Q-learning,20,867,1.0
Committed Q-learning,20,868,1.0
Committed Q-learning,20,869,1.0
Committed Q-learning,20,870,1.0
Committed Q-learning,20,871,1.0
Committed Q-learning,20,872,1.0
Committed Q-learning,20,873,1.0
Committed Q-learning,20,874,1.0
Committed Q-learning,20,875,1.0
Committed Q-learning,20,876,1.0
Committed Q-learning,20,877,1.0
Committed Q-learning,20,878,1.0
Committed Q-learning,20,879,1.0
Committed Q-learning,20,880,1.0
Committed Q-learning,20,881,1.0
Committed Q-learning,20,882,1.0
Committed Q-learning,20,883,1.0
Committed Q-learning,20,884,1.0
Committed Q-learning,20,885,1.0
Committed Q-learning,20,886,1.0
Committed Q-learning,20,887,1.0
Committed Q-learning,20,888,1.0
Committed Q-learning,20,889,1.0
Committed Q-learning,20,890,1.0
Committed Q-learning,20,891,1.0
Committed Q-learning,20,892,1.0
Committed Q-learning,20,893,1.0
Committed Q-learning,20,894,1.0
Committed Q-learning,20,895,1.0
Committed Q-learning,20,896,1.0
Committed Q-learning,20,897,1.0
Committed Q-learning,20,898,1.0
Committed Q-learning,20,899,1.0
Committed Q-learning,20,900,1.0
Committed Q-learning,20,901,1.0
Committed Q-learning,20,902,1.0
Committed Q-learning,20,903,1.0
Committed Q-learning,20,904,1.0
Committed Q-learning,20,905,1.0
Committed Q-learning,20,906,1.0
Committed Q-learning,20,907,1.0
Committed Q-learning,20,908,1.0
Committed Q-learning,20,909,1.0
Committed Q-learning,20,910,1.0
Committed Q-learning,20,911,1.0
Committed Q-learning,20,912,1.0
Committed Q-learning,20,913,1.0
Committed Q-learning,20,914,1.0
Committed Q-learning,20,915,1.0
Committed Q-learning,20,916,1.0
Committed Q-learning,20,917,1.0
Committed Q-learning,20,918,1.0
Committed Q-learning,20,919,1.0
Committed Q-learning,20,920,1.0
Committed Q-learning,20,921,1.0
Committed Q-learning,20,922,1.0
Committed Q-learning,20,923,1.0
Committed Q-learning,20,924,1.0
Committed Q-learning,20,925,1.0
Committed Q-learning,20,926,1.0
Committed Q-learning,20,927,1.0
Committed Q-learning,20,928,1.0
Committed Q-learning,20,929,1.0
Committed Q-learning,20,930,1.0
Committed Q-learning,20,931,1.0
Committed Q-learning,20,932,1.0
Committed Q-learning,20,933,1.0
Committed Q-learning,20,934,1.0
Committed Q-learning,20,935,1.0
Committed Q-learning,20,936,1.0
Committed Q-learning,20,937,1.0
Committed Q-learning,20,938,1.0
Committed Q-learning,20,939,1.0
Committed Q-learning,20,940,1.0
Committed Q-learning,20,941,1.0
Committed Q-learning,20,942,1.0
Committed Q-learning,20,943,1.0
Committed Q-learning,20,944,1.0
Committed Q-learning,20,945,1.0
Committed Q-learning,20,946,1.0
Committed Q-learning,20,947,1.0
Committed Q-learning,20,948,1.0
Committed Q-learning,20,949,1.0
Committed Q-learning,20,950,1.0
Committed Q-learning,20,951,1.0
Committed Q-learning,20,952,1.0
Committed Q-learning,20,953,1.0
Committed Q-learning,20,954,1.0
Committed Q-learning,20,955,1.0
Committed Q-learning,20,956,1.0
Committed Q-learning,20,957,1.0
Committed Q-learning,20,958,1.0
Committed Q-learning,20,959,1.0
Committed Q-learning,20,960,1.0
Committed Q-learning,20,961,1.0
Committed Q-learning,20,962,1.0
Committed Q-learning,20,963,1.0
Committed Q-learning,20,964,1.0
Committed Q-learning,20,965,1.0
Committed Q-learning,20,966,1.0
Committed Q-learning,20,967,1.0
Committed Q-learning,20,968,1.0
Committed Q-learning,20,969,1.0
Committed Q-learning,20,970,1.0
Committed Q-learning,20,971,1.0
Committed Q-learning,20,972,1.0
Committed Q-learning,20,973,1.0
Committed Q-learning,20,974,1.0
Committed Q-learning,20,975,1.0
Committed Q-learning,20,976,1.0
Committed Q-learning,20,977,1.0
Committed Q-learning,20,978,1.0
Committed Q-learning,20,979,1.0
Committed Q-learning,20,980,1.0
Committed Q-learning,20,981,1.0
Committed Q-learning,20,982,1.0
Committed Q-learning,20,983,1.0
Committed Q-learning,20,984,1.0
Committed Q-learning,20,985,1.0
Committed Q-learning,20,986,1.0
Committed Q-learning,20,987,1.0
Committed Q-learning,20,988,1.0
Committed Q-learning,20,989,1.0
Committed Q-learning,20,990,1.0
Committed Q-learning,20,991,1.0
Committed Q-learning,20,992,1.0
Committed Q-learning,20,993,1.0
Committed Q-learning,20,994,1.0
Committed Q-learning,20,995,1.0
Committed Q-learning,20,996,1.0
Committed Q-learning,20,997,1.0
Committed Q-learning,20,998,1.0
Committed Q-learning,20,999,1.0
Committed Q-learning,20,1000,1.0
Committed Q-learning,50,1,0.26100000739097595
Committed Q-learning,50,2,0.21299999952316284
Committed Q-learning,50,3,0.13699999451637268
Committed Q-learning,50,4,0.07100000232458115
Committed Q-learning,50,5,0.026000000536441803
Committed Q-learning,50,6,0.023000000044703484
Committed Q-learning,50,7,0.02199999988079071
Committed Q-learning,50,8,0.012000000104308128
Committed Q-learning,50,9,0.014000000432133675
Committed Q-learning,50,10,0.010999999940395355
Committed Q-learning,50,11,0.01600000075995922
Committed Q-learning,50,12,0.014999999664723873
Committed Q-learning,50,13,0.014999999664723873
Committed Q-learning,50,14,0.017000000923871994
Committed Q-learning,50,15,0.023000000044703484
Committed Q-learning,50,16,0.02500000037252903
Committed Q-learning,50,17,0.012000000104308128
Committed Q-learning,50,18,0.01600000075995922
Committed Q-learning,50,19,0.023000000044703484
Committed Q-learning,50,20,0.014999999664723873
Committed Q-learning,50,21,0.017999999225139618
Committed Q-learning,50,22,0.00800000037997961
Committed Q-learning,50,23,0.008999999612569809
Committed Q-learning,50,24,0.010999999940395355
Committed Q-learning,50,25,0.008999999612569809
Committed Q-learning,50,26,0.00800000037997961
Committed Q-learning,50,27,0.003000000026077032
Committed Q-learning,50,28,0.004999999888241291
Committed Q-learning,50,29,0.003000000026077032
Committed Q-learning,50,30,0.0020000000949949026
Committed Q-learning,50,31,0.0020000000949949026
Committed Q-learning,50,32,0.0010000000474974513
Committed Q-learning,50,33,0.0020000000949949026
Committed Q-learning,50,34,0.0020000000949949026
Committed Q-learning,50,35,0.0010000000474974513
Committed Q-learning,50,36,0.0010000000474974513
Committed Q-learning,50,37,0.0020000000949949026
Committed Q-learning,50,38,0.0
Committed Q-learning,50,39,0.0020000000949949026
Committed Q-learning,50,40,0.0
Committed Q-learning,50,41,0.0
Committed Q-learning,50,42,0.0
Committed Q-learning,50,43,0.0010000000474974513
Committed Q-learning,50,44,0.0
Committed Q-learning,50,45,0.0010000000474974513
Committed Q-learning,50,46,0.0010000000474974513
Committed Q-learning,50,47,0.0
Committed Q-learning,50,48,0.0
Committed Q-learning,50,49,0.0
Committed Q-learning,50,50,0.0
Committed Q-learning,50,51,0.06599999964237213
Committed Q-learning,50,52,0.23800000548362732
Committed Q-learning,50,53,0.3659999966621399
Committed Q-learning,50,54,0.4480000138282776
Committed Q-learning,50,55,0.5210000276565552
Committed Q-learning,50,56,0.5569999814033508
Committed Q-learning,50,57,0.5920000076293945
Committed Q-learning,50,58,0.621999979019165
Committed Q-learning,50,59,0.6439999938011169
Committed Q-learning,50,60,0.6639999747276306
Committed Q-learning,50,61,0.6840000152587891
Committed Q-learning,50,62,0.7020000219345093
Committed Q-learning,50,63,0.7239999771118164
Committed Q-learning,50,64,0.7409999966621399
Committed Q-learning,50,65,0.7630000114440918
Committed Q-learning,50,66,0.7839999794960022
Committed Q-learning,50,67,0.7979999780654907
Committed Q-learning,50,68,0.8270000219345093
Committed Q-learning,50,69,0.843999981880188
Committed Q-learning,50,70,0.859000027179718
Committed Q-learning,50,71,0.878000020980835
Committed Q-learning,50,72,0.8960000276565552
Committed Q-learning,50,73,0.9079999923706055
Committed Q-learning,50,74,0.9240000247955322
Committed Q-learning,50,75,0.9259999990463257
Committed Q-learning,50,76,0.9380000233650208
Committed Q-learning,50,77,0.9459999799728394
Committed Q-learning,50,78,0.9559999704360962
Committed Q-learning,50,79,0.9610000252723694
Committed Q-learning,50,80,0.9660000205039978
Committed Q-learning,50,81,0.968999981880188
Committed Q-learning,50,82,0.9700000286102295
Committed Q-learning,50,83,0.9729999899864197
Committed Q-learning,50,84,0.9760000109672546
Committed Q-learning,50,85,0.9769999980926514
Committed Q-learning,50,86,0.9800000190734863
Committed Q-learning,50,87,0.9800000190734863
Committed Q-learning,50,88,0.9810000061988831
Committed Q-learning,50,89,0.9829999804496765
Committed Q-learning,50,90,0.9829999804496765
Committed Q-learning,50,91,0.9829999804496765
Committed Q-learning,50,92,0.984000027179718
Committed Q-learning,50,93,0.9850000143051147
Committed Q-learning,50,94,0.9269999861717224
Committed Q-learning,50,95,0.7699999809265137
Committed Q-learning,50,96,0.6629999876022339
Committed Q-learning,50,97,0.578000009059906
Committed Q-learning,50,98,0.5049999952316284
Committed Q-learning,50,99,0.4410000145435333
Committed Q-learning,50,100,0.39399999380111694
Committed Q-learning,50,101,0.36800000071525574
Committed Q-learning,50,102,0.38999998569488525
Committed Q-learning,50,103,0.5260000228881836
Committed Q-learning,50,104,0.6389999985694885
Committed Q-learning,50,105,0.7009999752044678
Committed Q-learning,50,106,0.7490000128746033
Committed Q-learning,50,107,0.7770000100135803
Committed Q-learning,50,108,0.8050000071525574
Committed Q-learning,50,109,0.8040000200271606
Committed Q-learning,50,110,0.800000011920929
Committed Q-learning,50,111,0.8119999766349792
Committed Q-learning,50,112,0.8029999732971191
Committed Q-learning,50,113,0.8100000023841858
Committed Q-learning,50,114,0.8109999895095825
Committed Q-learning,50,115,0.8190000057220459
Committed Q-learning,50,116,0.8330000042915344
Committed Q-learning,50,117,0.8370000123977661
Committed Q-learning,50,118,0.8429999947547913
Committed Q-learning,50,119,0.8669999837875366
Committed Q-learning,50,120,0.8769999742507935
Committed Q-learning,50,121,0.8870000243186951
Committed Q-learning,50,122,0.9089999794960022
Committed Q-learning,50,123,0.921999990940094
Committed Q-learning,50,124,0.9300000071525574
Committed Q-learning,50,125,0.9430000185966492
Committed Q-learning,50,126,0.9459999799728394
Committed Q-learning,50,127,0.9539999961853027
Committed Q-learning,50,128,0.9620000123977661
Committed Q-learning,50,129,0.9710000157356262
Committed Q-learning,50,130,0.9779999852180481
Committed Q-learning,50,131,0.9810000061988831
Committed Q-learning,50,132,0.9850000143051147
Committed Q-learning,50,133,0.9850000143051147
Committed Q-learning,50,134,0.9879999756813049
Committed Q-learning,50,135,0.9909999966621399
Committed Q-learning,50,136,0.9929999709129333
Committed Q-learning,50,137,0.9940000176429749
Committed Q-learning,50,138,0.9940000176429749
Committed Q-learning,50,139,0.9940000176429749
Committed Q-learning,50,140,0.9950000047683716
Committed Q-learning,50,141,0.9950000047683716
Committed Q-learning,50,142,0.9950000047683716
Committed Q-learning,50,143,0.9959999918937683
Committed Q-learning,50,144,0.9959999918937683
Committed Q-learning,50,145,0.996999979019165
Committed Q-learning,50,146,0.996999979019165
Committed Q-learning,50,147,0.996999979019165
Committed Q-learning,50,148,0.9980000257492065
Committed Q-learning,50,149,0.9980000257492065
Committed Q-learning,50,150,0.9980000257492065
Committed Q-learning,50,151,0.9990000128746033
Committed Q-learning,50,152,0.9879999756813049
Committed Q-learning,50,153,0.9589999914169312
Committed Q-learning,50,154,0.968999981880188
Committed Q-learning,50,155,0.9800000190734863
Committed Q-learning,50,156,0.968999981880188
Committed Q-learning,50,157,0.9800000190734863
Committed Q-learning,50,158,0.9700000286102295
Committed Q-learning,50,159,0.9760000109672546
Committed Q-learning,50,160,0.9710000157356262
Committed Q-learning,50,161,0.9710000157356262
Committed Q-learning,50,162,0.9739999771118164
Committed Q-learning,50,163,0.9649999737739563
Committed Q-learning,50,164,0.9639999866485596
Committed Q-learning,50,165,0.9589999914169312
Committed Q-learning,50,166,0.9660000205039978
Committed Q-learning,50,167,0.9710000157356262
Committed Q-learning,50,168,0.949999988079071
Committed Q-learning,50,169,0.953000009059906
Committed Q-learning,50,170,0.9549999833106995
Committed Q-learning,50,171,0.9549999833106995
Committed Q-learning,50,172,0.9470000267028809
Committed Q-learning,50,173,0.9570000171661377
Committed Q-learning,50,174,0.968999981880188
Committed Q-learning,50,175,0.9750000238418579
Committed Q-learning,50,176,0.9779999852180481
Committed Q-learning,50,177,0.9710000157356262
Committed Q-learning,50,178,0.9729999899864197
Committed Q-learning,50,179,0.9760000109672546
Committed Q-learning,50,180,0.9850000143051147
Committed Q-learning,50,181,0.9879999756813049
Committed Q-learning,50,182,0.9900000095367432
Committed Q-learning,50,183,0.9900000095367432
Committed Q-learning,50,184,0.9900000095367432
Committed Q-learning,50,185,0.9929999709129333
Committed Q-learning,50,186,0.9950000047683716
Committed Q-learning,50,187,0.9959999918937683
Committed Q-learning,50,188,0.996999979019165
Committed Q-learning,50,189,0.996999979019165
Committed Q-learning,50,190,0.996999979019165
Committed Q-learning,50,191,0.9990000128746033
Committed Q-learning,50,192,0.9980000257492065
Committed Q-learning,50,193,0.9980000257492065
Committed Q-learning,50,194,0.9980000257492065
Committed Q-learning,50,195,0.9980000257492065
Committed Q-learning,50,196,0.9990000128746033
Committed Q-learning,50,197,0.9980000257492065
Committed Q-learning,50,198,0.9980000257492065
Committed Q-learning,50,199,0.9980000257492065
Committed Q-learning,50,200,0.9980000257492065
Committed Q-learning,50,201,0.9980000257492065
Committed Q-learning,50,202,0.9990000128746033
Committed Q-learning,50,203,1.0
Committed Q-learning,50,204,1.0
Committed Q-learning,50,205,1.0
Committed Q-learning,50,206,1.0
Committed Q-learning,50,207,1.0
Committed Q-learning,50,208,1.0
Committed Q-learning,50,209,1.0
Committed Q-learning,50,210,1.0
Committed Q-learning,50,211,1.0
Committed Q-learning,50,212,1.0
Committed Q-learning,50,213,1.0
Committed Q-learning,50,214,1.0
Committed Q-learning,50,215,1.0
Committed Q-learning,50,216,1.0
Committed Q-learning,50,217,1.0
Committed Q-learning,50,218,1.0
Committed Q-learning,50,219,1.0
Committed Q-learning,50,220,1.0
Committed Q-learning,50,221,1.0
Committed Q-learning,50,222,1.0
Committed Q-learning,50,223,1.0
Committed Q-learning,50,224,1.0
Committed Q-learning,50,225,1.0
Committed Q-learning,50,226,1.0
Committed Q-learning,50,227,1.0
Committed Q-learning,50,228,1.0
Committed Q-learning,50,229,1.0
Committed Q-learning,50,230,1.0
Committed Q-learning,50,231,1.0
Committed Q-learning,50,232,1.0
Committed Q-learning,50,233,1.0
Committed Q-learning,50,234,1.0
Committed Q-learning,50,235,1.0
Committed Q-learning,50,236,1.0
Committed Q-learning,50,237,1.0
Committed Q-learning,50,238,1.0
Committed Q-learning,50,239,1.0
Committed Q-learning,50,240,1.0
Committed Q-learning,50,241,1.0
Committed Q-learning,50,242,1.0
Committed Q-learning,50,243,1.0
Committed Q-learning,50,244,1.0
Committed Q-learning,50,245,1.0
Committed Q-learning,50,246,1.0
Committed Q-learning,50,247,1.0
Committed Q-learning,50,248,1.0
Committed Q-learning,50,249,1.0
Committed Q-learning,50,250,1.0
Committed Q-learning,50,251,1.0
Committed Q-learning,50,252,1.0
Committed Q-learning,50,253,1.0
Committed Q-learning,50,254,1.0
Committed Q-learning,50,255,1.0
Committed Q-learning,50,256,1.0
Committed Q-learning,50,257,1.0
Committed Q-learning,50,258,1.0
Committed Q-learning,50,259,1.0
Committed Q-learning,50,260,1.0
Committed Q-learning,50,261,1.0
Committed Q-learning,50,262,1.0
Committed Q-learning,50,263,1.0
Committed Q-learning,50,264,1.0
Committed Q-learning,50,265,1.0
Committed Q-learning,50,266,1.0
Committed Q-learning,50,267,1.0
Committed Q-learning,50,268,1.0
Committed Q-learning,50,269,1.0
Committed Q-learning,50,270,1.0
Committed Q-learning,50,271,1.0
Committed Q-learning,50,272,1.0
Committed Q-learning,50,273,1.0
Committed Q-learning,50,274,1.0
Committed Q-learning,50,275,1.0
Committed Q-learning,50,276,1.0
Committed Q-learning,50,277,1.0
Committed Q-learning,50,278,1.0
Committed Q-learning,50,279,1.0
Committed Q-learning,50,280,1.0
Committed Q-learning,50,281,1.0
Committed Q-learning,50,282,1.0
Committed Q-learning,50,283,1.0
Committed Q-learning,50,284,1.0
Committed Q-learning,50,285,1.0
Committed Q-learning,50,286,1.0
Committed Q-learning,50,287,1.0
Committed Q-learning,50,288,1.0
Committed Q-learning,50,289,1.0
Committed Q-learning,50,290,1.0
Committed Q-learning,50,291,1.0
Committed Q-learning,50,292,1.0
Committed Q-learning,50,293,1.0
Committed Q-learning,50,294,1.0
Committed Q-learning,50,295,1.0
Committed Q-learning,50,296,1.0
Committed Q-learning,50,297,1.0
Committed Q-learning,50,298,1.0
Committed Q-learning,50,299,1.0
Committed Q-learning,50,300,1.0
Committed Q-learning,50,301,1.0
Committed Q-learning,50,302,1.0
Committed Q-learning,50,303,1.0
Committed Q-learning,50,304,1.0
Committed Q-learning,50,305,1.0
Committed Q-learning,50,306,1.0
Committed Q-learning,50,307,1.0
Committed Q-learning,50,308,1.0
Committed Q-learning,50,309,1.0
Committed Q-learning,50,310,1.0
Committed Q-learning,50,311,1.0
Committed Q-learning,50,312,1.0
Committed Q-learning,50,313,1.0
Committed Q-learning,50,314,1.0
Committed Q-learning,50,315,1.0
Committed Q-learning,50,316,1.0
Committed Q-learning,50,317,1.0
Committed Q-learning,50,318,1.0
Committed Q-learning,50,319,1.0
Committed Q-learning,50,320,1.0
Committed Q-learning,50,321,1.0
Committed Q-learning,50,322,1.0
Committed Q-learning,50,323,1.0
Committed Q-learning,50,324,1.0
Committed Q-learning,50,325,1.0
Committed Q-learning,50,326,1.0
Committed Q-learning,50,327,1.0
Committed Q-learning,50,328,1.0
Committed Q-learning,50,329,1.0
Committed Q-learning,50,330,1.0
Committed Q-learning,50,331,1.0
Committed Q-learning,50,332,1.0
Committed Q-learning,50,333,1.0
Committed Q-learning,50,334,1.0
Committed Q-learning,50,335,1.0
Committed Q-learning,50,336,1.0
Committed Q-learning,50,337,1.0
Committed Q-learning,50,338,1.0
Committed Q-learning,50,339,1.0
Committed Q-learning,50,340,1.0
Committed Q-learning,50,341,1.0
Committed Q-learning,50,342,1.0
Committed Q-learning,50,343,1.0
Committed Q-learning,50,344,1.0
Committed Q-learning,50,345,1.0
Committed Q-learning,50,346,1.0
Committed Q-learning,50,347,1.0
Committed Q-learning,50,348,1.0
Committed Q-learning,50,349,1.0
Committed Q-learning,50,350,1.0
Committed Q-learning,50,351,1.0
Committed Q-learning,50,352,1.0
Committed Q-learning,50,353,1.0
Committed Q-learning,50,354,1.0
Committed Q-learning,50,355,1.0
Committed Q-learning,50,356,1.0
Committed Q-learning,50,357,1.0
Committed Q-learning,50,358,1.0
Committed Q-learning,50,359,1.0
Committed Q-learning,50,360,1.0
Committed Q-learning,50,361,1.0
Committed Q-learning,50,362,1.0
Committed Q-learning,50,363,1.0
Committed Q-learning,50,364,1.0
Committed Q-learning,50,365,1.0
Committed Q-learning,50,366,1.0
Committed Q-learning,50,367,1.0
Committed Q-learning,50,368,1.0
Committed Q-learning,50,369,1.0
Committed Q-learning,50,370,1.0
Committed Q-learning,50,371,1.0
Committed Q-learning,50,372,1.0
Committed Q-learning,50,373,1.0
Committed Q-learning,50,374,1.0
Committed Q-learning,50,375,1.0
Committed Q-learning,50,376,1.0
Committed Q-learning,50,377,1.0
Committed Q-learning,50,378,1.0
Committed Q-learning,50,379,1.0
Committed Q-learning,50,380,1.0
Committed Q-learning,50,381,1.0
Committed Q-learning,50,382,1.0
Committed Q-learning,50,383,1.0
Committed Q-learning,50,384,1.0
Committed Q-learning,50,385,1.0
Committed Q-learning,50,386,1.0
Committed Q-learning,50,387,1.0
Committed Q-learning,50,388,1.0
Committed Q-learning,50,389,1.0
Committed Q-learning,50,390,1.0
Committed Q-learning,50,391,1.0
Committed Q-learning,50,392,1.0
Committed Q-learning,50,393,1.0
Committed Q-learning,50,394,1.0
Committed Q-learning,50,395,1.0
Committed Q-learning,50,396,1.0
Committed Q-learning,50,397,1.0
Committed Q-learning,50,398,1.0
Committed Q-learning,50,399,1.0
Committed Q-learning,50,400,1.0
Committed Q-learning,50,401,1.0
Committed Q-learning,50,402,1.0
Committed Q-learning,50,403,1.0
Committed Q-learning,50,404,1.0
Committed Q-learning,50,405,1.0
Committed Q-learning,50,406,1.0
Committed Q-learning,50,407,1.0
Committed Q-learning,50,408,1.0
Committed Q-learning,50,409,1.0
Committed Q-learning,50,410,1.0
Committed Q-learning,50,411,1.0
Committed Q-learning,50,412,1.0
Committed Q-learning,50,413,1.0
Committed Q-learning,50,414,1.0
Committed Q-learning,50,415,1.0
Committed Q-learning,50,416,1.0
Committed Q-learning,50,417,1.0
Committed Q-learning,50,418,1.0
Committed Q-learning,50,419,1.0
Committed Q-learning,50,420,1.0
Committed Q-learning,50,421,1.0
Committed Q-learning,50,422,1.0
Committed Q-learning,50,423,1.0
Committed Q-learning,50,424,1.0
Committed Q-learning,50,425,1.0
Committed Q-learning,50,426,1.0
Committed Q-learning,50,427,1.0
Committed Q-learning,50,428,1.0
Committed Q-learning,50,429,1.0
Committed Q-learning,50,430,1.0
Committed Q-learning,50,431,1.0
Committed Q-learning,50,432,1.0
Committed Q-learning,50,433,1.0
Committed Q-learning,50,434,1.0
Committed Q-learning,50,435,1.0
Committed Q-learning,50,436,1.0
Committed Q-learning,50,437,1.0
Committed Q-learning,50,438,1.0
Committed Q-learning,50,439,1.0
Committed Q-learning,50,440,1.0
Committed Q-learning,50,441,1.0
Committed Q-learning,50,442,1.0
Committed Q-learning,50,443,1.0
Committed Q-learning,50,444,1.0
Committed Q-learning,50,445,1.0
Committed Q-learning,50,446,1.0
Committed Q-learning,50,447,1.0
Committed Q-learning,50,448,1.0
Committed Q-learning,50,449,1.0
Committed Q-learning,50,450,1.0
Committed Q-learning,50,451,1.0
Committed Q-learning,50,452,1.0
Committed Q-learning,50,453,1.0
Committed Q-learning,50,454,1.0
Committed Q-learning,50,455,1.0
Committed Q-learning,50,456,1.0
Committed Q-learning,50,457,1.0
Committed Q-learning,50,458,1.0
Committed Q-learning,50,459,1.0
Committed Q-learning,50,460,1.0
Committed Q-learning,50,461,1.0
Committed Q-learning,50,462,1.0
Committed Q-learning,50,463,1.0
Committed Q-learning,50,464,1.0
Committed Q-learning,50,465,1.0
Committed Q-learning,50,466,1.0
Committed Q-learning,50,467,1.0
Committed Q-learning,50,468,1.0
Committed Q-learning,50,469,1.0
Committed Q-learning,50,470,1.0
Committed Q-learning,50,471,1.0
Committed Q-learning,50,472,1.0
Committed Q-learning,50,473,1.0
Committed Q-learning,50,474,1.0
Committed Q-learning,50,475,1.0
Committed Q-learning,50,476,1.0
Committed Q-learning,50,477,1.0
Committed Q-learning,50,478,1.0
Committed Q-learning,50,479,1.0
Committed Q-learning,50,480,1.0
Committed Q-learning,50,481,1.0
Committed Q-learning,50,482,1.0
Committed Q-learning,50,483,1.0
Committed Q-learning,50,484,1.0
Committed Q-learning,50,485,1.0
Committed Q-learning,50,486,1.0
Committed Q-learning,50,487,1.0
Committed Q-learning,50,488,1.0
Committed Q-learning,50,489,1.0
Committed Q-learning,50,490,1.0
Committed Q-learning,50,491,1.0
Committed Q-learning,50,492,1.0
Committed Q-learning,50,493,1.0
Committed Q-learning,50,494,1.0
Committed Q-learning,50,495,1.0
Committed Q-learning,50,496,1.0
Committed Q-learning,50,497,1.0
Committed Q-learning,50,498,1.0
Committed Q-learning,50,499,1.0
Committed Q-learning,50,500,1.0
Committed Q-learning,50,501,1.0
Committed Q-learning,50,502,1.0
Committed Q-learning,50,503,1.0
Committed Q-learning,50,504,1.0
Committed Q-learning,50,505,1.0
Committed Q-learning,50,506,1.0
Committed Q-learning,50,507,1.0
Committed Q-learning,50,508,1.0
Committed Q-learning,50,509,1.0
Committed Q-learning,50,510,1.0
Committed Q-learning,50,511,1.0
Committed Q-learning,50,512,1.0
Committed Q-learning,50,513,1.0
Committed Q-learning,50,514,1.0
Committed Q-learning,50,515,1.0
Committed Q-learning,50,516,1.0
Committed Q-learning,50,517,1.0
Committed Q-learning,50,518,1.0
Committed Q-learning,50,519,1.0
Committed Q-learning,50,520,1.0
Committed Q-learning,50,521,1.0
Committed Q-learning,50,522,1.0
Committed Q-learning,50,523,1.0
Committed Q-learning,50,524,1.0
Committed Q-learning,50,525,1.0
Committed Q-learning,50,526,1.0
Committed Q-learning,50,527,1.0
Committed Q-learning,50,528,1.0
Committed Q-learning,50,529,1.0
Committed Q-learning,50,530,1.0
Committed Q-learning,50,531,1.0
Committed Q-learning,50,532,1.0
Committed Q-learning,50,533,1.0
Committed Q-learning,50,534,1.0
Committed Q-learning,50,535,1.0
Committed Q-learning,50,536,1.0
Committed Q-learning,50,537,1.0
Committed Q-learning,50,538,1.0
Committed Q-learning,50,539,1.0
Committed Q-learning,50,540,1.0
Committed Q-learning,50,541,1.0
Committed Q-learning,50,542,1.0
Committed Q-learning,50,543,1.0
Committed Q-learning,50,544,1.0
Committed Q-learning,50,545,1.0
Committed Q-learning,50,546,1.0
Committed Q-learning,50,547,1.0
Committed Q-learning,50,548,1.0
Committed Q-learning,50,549,1.0
Committed Q-learning,50,550,1.0
Committed Q-learning,50,551,1.0
Committed Q-learning,50,552,1.0
Committed Q-learning,50,553,1.0
Committed Q-learning,50,554,1.0
Committed Q-learning,50,555,1.0
Committed Q-learning,50,556,1.0
Committed Q-learning,50,557,1.0
Committed Q-learning,50,558,1.0
Committed Q-learning,50,559,1.0
Committed Q-learning,50,560,1.0
Committed Q-learning,50,561,1.0
Committed Q-learning,50,562,1.0
Committed Q-learning,50,563,1.0
Committed Q-learning,50,564,1.0
Committed Q-learning,50,565,1.0
Committed Q-learning,50,566,1.0
Committed Q-learning,50,567,1.0
Committed Q-learning,50,568,1.0
Committed Q-learning,50,569,1.0
Committed Q-learning,50,570,1.0
Committed Q-learning,50,571,1.0
Committed Q-learning,50,572,1.0
Committed Q-learning,50,573,1.0
Committed Q-learning,50,574,1.0
Committed Q-learning,50,575,1.0
Committed Q-learning,50,576,1.0
Committed Q-learning,50,577,1.0
Committed Q-learning,50,578,1.0
Committed Q-learning,50,579,1.0
Committed Q-learning,50,580,1.0
Committed Q-learning,50,581,1.0
Committed Q-learning,50,582,1.0
Committed Q-learning,50,583,1.0
Committed Q-learning,50,584,1.0
Committed Q-learning,50,585,1.0
Committed Q-learning,50,586,1.0
Committed Q-learning,50,587,1.0
Committed Q-learning,50,588,1.0
Committed Q-learning,50,589,1.0
Committed Q-learning,50,590,1.0
Committed Q-learning,50,591,1.0
Committed Q-learning,50,592,1.0
Committed Q-learning,50,593,1.0
Committed Q-learning,50,594,1.0
Committed Q-learning,50,595,1.0
Committed Q-learning,50,596,1.0
Committed Q-learning,50,597,1.0
Committed Q-learning,50,598,1.0
Committed Q-learning,50,599,1.0
Committed Q-learning,50,600,1.0
Committed Q-learning,50,601,1.0
Committed Q-learning,50,602,1.0
Committed Q-learning,50,603,1.0
Committed Q-learning,50,604,1.0
Committed Q-learning,50,605,1.0
Committed Q-learning,50,606,1.0
Committed Q-learning,50,607,1.0
Committed Q-learning,50,608,1.0
Committed Q-learning,50,609,1.0
Committed Q-learning,50,610,1.0
Committed Q-learning,50,611,1.0
Committed Q-learning,50,612,1.0
Committed Q-learning,50,613,1.0
Committed Q-learning,50,614,1.0
Committed Q-learning,50,615,1.0
Committed Q-learning,50,616,1.0
Committed Q-learning,50,617,1.0
Committed Q-learning,50,618,1.0
Committed Q-learning,50,619,1.0
Committed Q-learning,50,620,1.0
Committed Q-learning,50,621,1.0
Committed Q-learning,50,622,1.0
Committed Q-learning,50,623,1.0
Committed Q-learning,50,624,1.0
Committed Q-learning,50,625,1.0
Committed Q-learning,50,626,1.0
Committed Q-learning,50,627,1.0
Committed Q-learning,50,628,1.0
Committed Q-learning,50,629,1.0
Committed Q-learning,50,630,1.0
Committed Q-learning,50,631,1.0
Committed Q-learning,50,632,1.0
Committed Q-learning,50,633,1.0
Committed Q-learning,50,634,1.0
Committed Q-learning,50,635,1.0
Committed Q-learning,50,636,1.0
Committed Q-learning,50,637,1.0
Committed Q-learning,50,638,1.0
Committed Q-learning,50,639,1.0
Committed Q-learning,50,640,1.0
Committed Q-learning,50,641,1.0
Committed Q-learning,50,642,1.0
Committed Q-learning,50,643,1.0
Committed Q-learning,50,644,1.0
Committed Q-learning,50,645,1.0
Committed Q-learning,50,646,1.0
Committed Q-learning,50,647,1.0
Committed Q-learning,50,648,1.0
Committed Q-learning,50,649,1.0
Committed Q-learning,50,650,1.0
Committed Q-learning,50,651,1.0
Committed Q-learning,50,652,1.0
Committed Q-learning,50,653,1.0
Committed Q-learning,50,654,1.0
Committed Q-learning,50,655,1.0
Committed Q-learning,50,656,1.0
Committed Q-learning,50,657,1.0
Committed Q-learning,50,658,1.0
Committed Q-learning,50,659,1.0
Committed Q-learning,50,660,1.0
Committed Q-learning,50,661,1.0
Committed Q-learning,50,662,1.0
Committed Q-learning,50,663,1.0
Committed Q-learning,50,664,1.0
Committed Q-learning,50,665,1.0
Committed Q-learning,50,666,1.0
Committed Q-learning,50,667,1.0
Committed Q-learning,50,668,1.0
Committed Q-learning,50,669,1.0
Committed Q-learning,50,670,1.0
Committed Q-learning,50,671,1.0
Committed Q-learning,50,672,1.0
Committed Q-learning,50,673,1.0
Committed Q-learning,50,674,1.0
Committed Q-learning,50,675,1.0
Committed Q-learning,50,676,1.0
Committed Q-learning,50,677,1.0
Committed Q-learning,50,678,1.0
Committed Q-learning,50,679,1.0
Committed Q-learning,50,680,1.0
Committed Q-learning,50,681,1.0
Committed Q-learning,50,682,1.0
Committed Q-learning,50,683,1.0
Committed Q-learning,50,684,1.0
Committed Q-learning,50,685,1.0
Committed Q-learning,50,686,1.0
Committed Q-learning,50,687,1.0
Committed Q-learning,50,688,1.0
Committed Q-learning,50,689,1.0
Committed Q-learning,50,690,1.0
Committed Q-learning,50,691,1.0
Committed Q-learning,50,692,1.0
Committed Q-learning,50,693,1.0
Committed Q-learning,50,694,1.0
Committed Q-learning,50,695,1.0
Committed Q-learning,50,696,1.0
Committed Q-learning,50,697,1.0
Committed Q-learning,50,698,1.0
Committed Q-learning,50,699,1.0
Committed Q-learning,50,700,1.0
Committed Q-learning,50,701,1.0
Committed Q-learning,50,702,1.0
Committed Q-learning,50,703,1.0
Committed Q-learning,50,704,1.0
Committed Q-learning,50,705,1.0
Committed Q-learning,50,706,1.0
Committed Q-learning,50,707,1.0
Committed Q-learning,50,708,1.0
Committed Q-learning,50,709,1.0
Committed Q-learning,50,710,1.0
Committed Q-learning,50,711,1.0
Committed Q-learning,50,712,1.0
Committed Q-learning,50,713,1.0
Committed Q-learning,50,714,1.0
Committed Q-learning,50,715,1.0
Committed Q-learning,50,716,1.0
Committed Q-learning,50,717,1.0
Committed Q-learning,50,718,1.0
Committed Q-learning,50,719,1.0
Committed Q-learning,50,720,1.0
Committed Q-learning,50,721,1.0
Committed Q-learning,50,722,1.0
Committed Q-learning,50,723,1.0
Committed Q-learning,50,724,1.0
Committed Q-learning,50,725,1.0
Committed Q-learning,50,726,1.0
Committed Q-learning,50,727,1.0
Committed Q-learning,50,728,1.0
Committed Q-learning,50,729,1.0
Committed Q-learning,50,730,1.0
Committed Q-learning,50,731,1.0
Committed Q-learning,50,732,1.0
Committed Q-learning,50,733,1.0
Committed Q-learning,50,734,1.0
Committed Q-learning,50,735,1.0
Committed Q-learning,50,736,1.0
Committed Q-learning,50,737,1.0
Committed Q-learning,50,738,1.0
Committed Q-learning,50,739,1.0
Committed Q-learning,50,740,1.0
Committed Q-learning,50,741,1.0
Committed Q-learning,50,742,1.0
Committed Q-learning,50,743,1.0
Committed Q-learning,50,744,1.0
Committed Q-learning,50,745,1.0
Committed Q-learning,50,746,1.0
Committed Q-learning,50,747,1.0
Committed Q-learning,50,748,1.0
Committed Q-learning,50,749,1.0
Committed Q-learning,50,750,1.0
Committed Q-learning,50,751,1.0
Committed Q-learning,50,752,1.0
Committed Q-learning,50,753,1.0
Committed Q-learning,50,754,1.0
Committed Q-learning,50,755,1.0
Committed Q-learning,50,756,1.0
Committed Q-learning,50,757,1.0
Committed Q-learning,50,758,1.0
Committed Q-learning,50,759,1.0
Committed Q-learning,50,760,1.0
Committed Q-learning,50,761,1.0
Committed Q-learning,50,762,1.0
Committed Q-learning,50,763,1.0
Committed Q-learning,50,764,1.0
Committed Q-learning,50,765,1.0
Committed Q-learning,50,766,1.0
Committed Q-learning,50,767,1.0
Committed Q-learning,50,768,1.0
Committed Q-learning,50,769,1.0
Committed Q-learning,50,770,1.0
Committed Q-learning,50,771,1.0
Committed Q-learning,50,772,1.0
Committed Q-learning,50,773,1.0
Committed Q-learning,50,774,1.0
Committed Q-learning,50,775,1.0
Committed Q-learning,50,776,1.0
Committed Q-learning,50,777,1.0
Committed Q-learning,50,778,1.0
Committed Q-learning,50,779,1.0
Committed Q-learning,50,780,1.0
Committed Q-learning,50,781,1.0
Committed Q-learning,50,782,1.0
Committed Q-learning,50,783,1.0
Committed Q-learning,50,784,1.0
Committed Q-learning,50,785,1.0
Committed Q-learning,50,786,1.0
Committed Q-learning,50,787,1.0
Committed Q-learning,50,788,1.0
Committed Q-learning,50,789,1.0
Committed Q-learning,50,790,1.0
Committed Q-learning,50,791,1.0
Committed Q-learning,50,792,1.0
Committed Q-learning,50,793,1.0
Committed Q-learning,50,794,1.0
Committed Q-learning,50,795,1.0
Committed Q-learning,50,796,1.0
Committed Q-learning,50,797,1.0
Committed Q-learning,50,798,1.0
Committed Q-learning,50,799,1.0
Committed Q-learning,50,800,1.0
Committed Q-learning,50,801,1.0
Committed Q-learning,50,802,1.0
Committed Q-learning,50,803,1.0
Committed Q-learning,50,804,1.0
Committed Q-learning,50,805,1.0
Committed Q-learning,50,806,1.0
Committed Q-learning,50,807,1.0
Committed Q-learning,50,808,1.0
Committed Q-learning,50,809,1.0
Committed Q-learning,50,810,1.0
Committed Q-learning,50,811,1.0
Committed Q-learning,50,812,1.0
Committed Q-learning,50,813,1.0
Committed Q-learning,50,814,1.0
Committed Q-learning,50,815,1.0
Committed Q-learning,50,816,1.0
Committed Q-learning,50,817,1.0
Committed Q-learning,50,818,1.0
Committed Q-learning,50,819,1.0
Committed Q-learning,50,820,1.0
Committed Q-learning,50,821,1.0
Committed Q-learning,50,822,1.0
Committed Q-learning,50,823,1.0
Committed Q-learning,50,824,1.0
Committed Q-learning,50,825,1.0
Committed Q-learning,50,826,1.0
Committed Q-learning,50,827,1.0
Committed Q-learning,50,828,1.0
Committed Q-learning,50,829,1.0
Committed Q-learning,50,830,1.0
Committed Q-learning,50,831,1.0
Committed Q-learning,50,832,1.0
Committed Q-learning,50,833,1.0
Committed Q-learning,50,834,1.0
Committed Q-learning,50,835,1.0
Committed Q-learning,50,836,1.0
Committed Q-learning,50,837,1.0
Committed Q-learning,50,838,1.0
Committed Q-learning,50,839,1.0
Committed Q-learning,50,840,1.0
Committed Q-learning,50,841,1.0
Committed Q-learning,50,842,1.0
Committed Q-learning,50,843,1.0
Committed Q-learning,50,844,1.0
Committed Q-learning,50,845,1.0
Committed Q-learning,50,846,1.0
Committed Q-learning,50,847,1.0
Committed Q-learning,50,848,1.0
Committed Q-learning,50,849,1.0
Committed Q-learning,50,850,1.0
Committed Q-learning,50,851,1.0
Committed Q-learning,50,852,1.0
Committed Q-learning,50,853,1.0
Committed Q-learning,50,854,1.0
Committed Q-learning,50,855,1.0
Committed Q-learning,50,856,1.0
Committed Q-learning,50,857,1.0
Committed Q-learning,50,858,1.0
Committed Q-learning,50,859,1.0
Committed Q-learning,50,860,1.0
Committed Q-learning,50,861,1.0
Committed Q-learning,50,862,1.0
Committed Q-learning,50,863,1.0
Committed Q-learning,50,864,1.0
Committed Q-learning,50,865,1.0
Committed Q-learning,50,866,1.0
Committed Q-learning,50,867,1.0
Committed Q-learning,50,868,1.0
Committed Q-learning,50,869,1.0
Committed Q-learning,50,870,1.0
Committed Q-learning,50,871,1.0
Committed Q-learning,50,872,1.0
Committed Q-learning,50,873,1.0
Committed Q-learning,50,874,1.0
Committed Q-learning,50,875,1.0
Committed Q-learning,50,876,1.0
Committed Q-learning,50,877,1.0
Committed Q-learning,50,878,1.0
Committed Q-learning,50,879,1.0
Committed Q-learning,50,880,1.0
Committed Q-learning,50,881,1.0
Committed Q-learning,50,882,1.0
Committed Q-learning,50,883,1.0
Committed Q-learning,50,884,1.0
Committed Q-learning,50,885,1.0
Committed Q-learning,50,886,1.0
Committed Q-learning,50,887,1.0
Committed Q-learning,50,888,1.0
Committed Q-learning,50,889,1.0
Committed Q-learning,50,890,1.0
Committed Q-learning,50,891,1.0
Committed Q-learning,50,892,1.0
Committed Q-learning,50,893,1.0
Committed Q-learning,50,894,1.0
Committed Q-learning,50,895,1.0
Committed Q-learning,50,896,1.0
Committed Q-learning,50,897,1.0
Committed Q-learning,50,898,1.0
Committed Q-learning,50,899,1.0
Committed Q-learning,50,900,1.0
Committed Q-learning,50,901,1.0
Committed Q-learning,50,902,1.0
Committed Q-learning,50,903,1.0
Committed Q-learning,50,904,1.0
Committed Q-learning,50,905,1.0
Committed Q-learning,50,906,1.0
Committed Q-learning,50,907,1.0
Committed Q-learning,50,908,1.0
Committed Q-learning,50,909,1.0
Committed Q-learning,50,910,1.0
Committed Q-learning,50,911,1.0
Committed Q-learning,50,912,1.0
Committed Q-learning,50,913,1.0
Committed Q-learning,50,914,1.0
Committed Q-learning,50,915,1.0
Committed Q-learning,50,916,1.0
Committed Q-learning,50,917,1.0
Committed Q-learning,50,918,1.0
Committed Q-learning,50,919,1.0
Committed Q-learning,50,920,1.0
Committed Q-learning,50,921,1.0
Committed Q-learning,50,922,1.0
Committed Q-learning,50,923,1.0
Committed Q-learning,50,924,1.0
Committed Q-learning,50,925,1.0
Committed Q-learning,50,926,1.0
Committed Q-learning,50,927,1.0
Committed Q-learning,50,928,1.0
Committed Q-learning,50,929,1.0
Committed Q-learning,50,930,1.0
Committed Q-learning,50,931,1.0
Committed Q-learning,50,932,1.0
Committed Q-learning,50,933,1.0
Committed Q-learning,50,934,1.0
Committed Q-learning,50,935,1.0
Committed Q-learning,50,936,1.0
Committed Q-learning,50,937,1.0
Committed Q-learning,50,938,1.0
Committed Q-learning,50,939,1.0
Committed Q-learning,50,940,1.0
Committed Q-learning,50,941,1.0
Committed Q-learning,50,942,1.0
Committed Q-learning,50,943,1.0
Committed Q-learning,50,944,1.0
Committed Q-learning,50,945,1.0
Committed Q-learning,50,946,1.0
Committed Q-learning,50,947,1.0
Committed Q-learning,50,948,1.0
Committed Q-learning,50,949,1.0
Committed Q-learning,50,950,1.0
Committed Q-learning,50,951,1.0
Committed Q-learning,50,952,1.0
Committed Q-learning,50,953,1.0
Committed Q-learning,50,954,1.0
Committed Q-learning,50,955,1.0
Committed Q-learning,50,956,1.0
Committed Q-learning,50,957,1.0
Committed Q-learning,50,958,1.0
Committed Q-learning,50,959,1.0
Committed Q-learning,50,960,1.0
Committed Q-learning,50,961,1.0
Committed Q-learning,50,962,1.0
Committed Q-learning,50,963,1.0
Committed Q-learning,50,964,1.0
Committed Q-learning,50,965,1.0
Committed Q-learning,50,966,1.0
Committed Q-learning,50,967,1.0
Committed Q-learning,50,968,1.0
Committed Q-learning,50,969,1.0
Committed Q-learning,50,970,1.0
Committed Q-learning,50,971,1.0
Committed Q-learning,50,972,1.0
Committed Q-learning,50,973,1.0
Committed Q-learning,50,974,1.0
Committed Q-learning,50,975,1.0
Committed Q-learning,50,976,1.0
Committed Q-learning,50,977,1.0
Committed Q-learning,50,978,1.0
Committed Q-learning,50,979,1.0
Committed Q-learning,50,980,1.0
Committed Q-learning,50,981,1.0
Committed Q-learning,50,982,1.0
Committed Q-learning,50,983,1.0
Committed Q-learning,50,984,1.0
Committed Q-learning,50,985,1.0
Committed Q-learning,50,986,1.0
Committed Q-learning,50,987,1.0
Committed Q-learning,50,988,1.0
Committed Q-learning,50,989,1.0
Committed Q-learning,50,990,1.0
Committed Q-learning,50,991,1.0
Committed Q-learning,50,992,1.0
Committed Q-learning,50,993,1.0
Committed Q-learning,50,994,1.0
Committed Q-learning,50,995,1.0
Committed Q-learning,50,996,1.0
Committed Q-learning,50,997,1.0
Committed Q-learning,50,998,1.0
Committed Q-learning,50,999,1.0
Committed Q-learning,50,1000,1.0
Committed Q-learning,100,1,0.2840000092983246
Committed Q-learning,100,2,0.22599999606609344
Committed Q-learning,100,3,0.14100000262260437
Committed Q-learning,100,4,0.07699999958276749
Committed Q-learning,100,5,0.04500000178813934
Committed Q-learning,100,6,0.01899999938905239
Committed Q-learning,100,7,0.020999999716877937
Committed Q-learning,100,8,0.019999999552965164
Committed Q-learning,100,9,0.024000000208616257
Committed Q-learning,100,10,0.02500000037252903
Committed Q-learning,100,11,0.026000000536441803
Committed Q-learning,100,12,0.017999999225139618
Committed Q-learning,100,13,0.017000000923871994
Committed Q-learning,100,14,0.02199999988079071
Committed Q-learning,100,15,0.024000000208616257
Committed Q-learning,100,16,0.01600000075995922
Committed Q-learning,100,17,0.014000000432133675
Committed Q-learning,100,18,0.017999999225139618
Committed Q-learning,100,19,0.017000000923871994
Committed Q-learning,100,20,0.014000000432133675
Committed Q-learning,100,21,0.012000000104308128
Committed Q-learning,100,22,0.004000000189989805
Committed Q-learning,100,23,0.006000000052154064
Committed Q-learning,100,24,0.00800000037997961
Committed Q-learning,100,25,0.008999999612569809
Committed Q-learning,100,26,0.007000000216066837
Committed Q-learning,100,27,0.003000000026077032
Committed Q-learning,100,28,0.004000000189989805
Committed Q-learning,100,29,0.0020000000949949026
Committed Q-learning,100,30,0.0010000000474974513
Committed Q-learning,100,31,0.004000000189989805
Committed Q-learning,100,32,0.0020000000949949026
Committed Q-learning,100,33,0.0020000000949949026
Committed Q-learning,100,34,0.0010000000474974513
Committed Q-learning,100,35,0.0010000000474974513
Committed Q-learning,100,36,0.0010000000474974513
Committed Q-learning,100,37,0.0
Committed Q-learning,100,38,0.0010000000474974513
Committed Q-learning,100,39,0.0010000000474974513
Committed Q-learning,100,40,0.0
Committed Q-learning,100,41,0.0
Committed Q-learning,100,42,0.0
Committed Q-learning,100,43,0.0
Committed Q-learning,100,44,0.0
Committed Q-learning,100,45,0.0
Committed Q-learning,100,46,0.0
Committed Q-learning,100,47,0.0
Committed Q-learning,100,48,0.0
Committed Q-learning,100,49,0.0
Committed Q-learning,100,50,0.0
Committed Q-learning,100,51,0.0
Committed Q-learning,100,52,0.0
Committed Q-learning,100,53,0.0
Committed Q-learning,100,54,0.0
Committed Q-learning,100,55,0.0
Committed Q-learning,100,56,0.0
Committed Q-learning,100,57,0.0
Committed Q-learning,100,58,0.0
Committed Q-learning,100,59,0.0
Committed Q-learning,100,60,0.0
Committed Q-learning,100,61,0.0
Committed Q-learning,100,62,0.0
Committed Q-learning,100,63,0.0
Committed Q-learning,100,64,0.0
Committed Q-learning,100,65,0.0
Committed Q-learning,100,66,0.0
Committed Q-learning,100,67,0.0
Committed Q-learning,100,68,0.0
Committed Q-learning,100,69,0.0
Committed Q-learning,100,70,0.0
Committed Q-learning,100,71,0.0
Committed Q-learning,100,72,0.0
Committed Q-learning,100,73,0.0
Committed Q-learning,100,74,0.0
Committed Q-learning,100,75,0.0
Committed Q-learning,100,76,0.0
Committed Q-learning,100,77,0.0
Committed Q-learning,100,78,0.0
Committed Q-learning,100,79,0.0
Committed Q-learning,100,80,0.0
Committed Q-learning,100,81,0.0
Committed Q-learning,100,82,0.0
Committed Q-learning,100,83,0.0
Committed Q-learning,100,84,0.0
Committed Q-learning,100,85,0.0
Committed Q-learning,100,86,0.0
Committed Q-learning,100,87,0.0
Committed Q-learning,100,88,0.0
Committed Q-learning,100,89,0.0
Committed Q-learning,100,90,0.0
Committed Q-learning,100,91,0.0
Committed Q-learning,100,92,0.0
Committed Q-learning,100,93,0.0
Committed Q-learning,100,94,0.0
Committed Q-learning,100,95,0.0
Committed Q-learning,100,96,0.0
Committed Q-learning,100,97,0.0
Committed Q-learning,100,98,0.0
Committed Q-learning,100,99,0.0
Committed Q-learning,100,100,0.0
Committed Q-learning,100,101,0.06400000303983688
Committed Q-learning,100,102,0.2329999953508377
Committed Q-learning,100,103,0.335999995470047
Committed Q-learning,100,104,0.42500001192092896
Committed Q-learning,100,105,0.49799999594688416
Committed Q-learning,100,106,0.5540000200271606
Committed Q-learning,100,107,0.5910000205039978
Committed Q-learning,100,108,0.6209999918937683
Committed Q-learning,100,109,0.656000018119812
Committed Q-learning,100,110,0.6809999942779541
Committed Q-learning,100,111,0.7049999833106995
Committed Q-learning,100,112,0.7319999933242798
Committed Q-learning,100,113,0.7559999823570251
Committed Q-learning,100,114,0.7749999761581421
Committed Q-learning,100,115,0.7929999828338623
Committed Q-learning,100,116,0.8159999847412109
Committed Q-learning,100,117,0.8349999785423279
Committed Q-learning,100,118,0.8529999852180481
Committed Q-learning,100,119,0.8709999918937683
Committed Q-learning,100,120,0.890999972820282
Committed Q-learning,100,121,0.902999997138977
Committed Q-learning,100,122,0.9169999957084656
Committed Q-learning,100,123,0.9300000071525574
Committed Q-learning,100,124,0.9380000233650208
Committed Q-learning,100,125,0.9430000185966492
Committed Q-learning,100,126,0.9520000219345093
Committed Q-learning,100,127,0.9589999914169312
Committed Q-learning,100,128,0.9639999866485596
Committed Q-learning,100,129,0.9679999947547913
Committed Q-learning,100,130,0.9760000109672546
Committed Q-learning,100,131,0.9769999980926514
Committed Q-learning,100,132,0.9800000190734863
Committed Q-learning,100,133,0.9819999933242798
Committed Q-learning,100,134,0.9850000143051147
Committed Q-learning,100,135,0.9860000014305115
Committed Q-learning,100,136,0.9879999756813049
Committed Q-learning,100,137,0.9890000224113464
Committed Q-learning,100,138,0.9900000095367432
Committed Q-learning,100,139,0.9929999709129333
Committed Q-learning,100,140,0.9929999709129333
Committed Q-learning,100,141,0.9940000176429749
Committed Q-learning,100,142,0.9950000047683716
Committed Q-learning,100,143,0.9950000047683716
Committed Q-learning,100,144,0.9950000047683716
Committed Q-learning,100,145,0.9950000047683716
Committed Q-learning,100,146,0.9950000047683716
Committed Q-learning,100,147,0.9950000047683716
Committed Q-learning,100,148,0.9950000047683716
Committed Q-learning,100,149,0.9950000047683716
Committed Q-learning,100,150,0.9950000047683716
Committed Q-learning,100,151,0.9950000047683716
Committed Q-learning,100,152,0.9950000047683716
Committed Q-learning,100,153,0.9950000047683716
Committed Q-learning,100,154,0.9950000047683716
Committed Q-learning,100,155,0.9950000047683716
Committed Q-learning,100,156,0.9950000047683716
Committed Q-learning,100,157,0.9950000047683716
Committed Q-learning,100,158,0.9950000047683716
Committed Q-learning,100,159,0.9950000047683716
Committed Q-learning,100,160,0.9950000047683716
Committed Q-learning,100,161,0.9950000047683716
Committed Q-learning,100,162,0.9950000047683716
Committed Q-learning,100,163,0.9950000047683716
Committed Q-learning,100,164,0.9950000047683716
Committed Q-learning,100,165,0.9950000047683716
Committed Q-learning,100,166,0.9950000047683716
Committed Q-learning,100,167,0.9950000047683716
Committed Q-learning,100,168,0.9950000047683716
Committed Q-learning,100,169,0.9950000047683716
Committed Q-learning,100,170,0.9950000047683716
Committed Q-learning,100,171,0.9950000047683716
Committed Q-learning,100,172,0.9950000047683716
Committed Q-learning,100,173,0.9950000047683716
Committed Q-learning,100,174,0.9950000047683716
Committed Q-learning,100,175,0.9950000047683716
Committed Q-learning,100,176,0.9950000047683716
Committed Q-learning,100,177,0.9950000047683716
Committed Q-learning,100,178,0.9950000047683716
Committed Q-learning,100,179,0.9950000047683716
Committed Q-learning,100,180,0.9950000047683716
Committed Q-learning,100,181,0.9950000047683716
Committed Q-learning,100,182,0.9950000047683716
Committed Q-learning,100,183,0.9950000047683716
Committed Q-learning,100,184,0.9950000047683716
Committed Q-learning,100,185,0.9950000047683716
Committed Q-learning,100,186,0.9950000047683716
Committed Q-learning,100,187,0.9950000047683716
Committed Q-learning,100,188,0.9950000047683716
Committed Q-learning,100,189,0.9950000047683716
Committed Q-learning,100,190,0.9950000047683716
Committed Q-learning,100,191,0.9950000047683716
Committed Q-learning,100,192,0.9950000047683716
Committed Q-learning,100,193,0.9950000047683716
Committed Q-learning,100,194,0.9950000047683716
Committed Q-learning,100,195,0.9950000047683716
Committed Q-learning,100,196,0.9950000047683716
Committed Q-learning,100,197,0.9950000047683716
Committed Q-learning,100,198,0.9950000047683716
Committed Q-learning,100,199,0.9950000047683716
Committed Q-learning,100,200,0.9950000047683716
Committed Q-learning,100,201,0.9950000047683716
Committed Q-learning,100,202,0.9950000047683716
Committed Q-learning,100,203,0.9950000047683716
Committed Q-learning,100,204,0.9959999918937683
Committed Q-learning,100,205,0.996999979019165
Committed Q-learning,100,206,0.9980000257492065
Committed Q-learning,100,207,0.9980000257492065
Committed Q-learning,100,208,0.9980000257492065
Committed Q-learning,100,209,0.9909999966621399
Committed Q-learning,100,210,0.9919999837875366
Committed Q-learning,100,211,0.9919999837875366
Committed Q-learning,100,212,0.9860000014305115
Committed Q-learning,100,213,0.9850000143051147
Committed Q-learning,100,214,0.9879999756813049
Committed Q-learning,100,215,0.9800000190734863
Committed Q-learning,100,216,0.9729999899864197
Committed Q-learning,100,217,0.9739999771118164
Committed Q-learning,100,218,0.9750000238418579
Committed Q-learning,100,219,0.9670000076293945
Committed Q-learning,100,220,0.9729999899864197
Committed Q-learning,100,221,0.972000002861023
Committed Q-learning,100,222,0.9729999899864197
Committed Q-learning,100,223,0.9739999771118164
Committed Q-learning,100,224,0.9760000109672546
Committed Q-learning,100,225,0.9800000190734863
Committed Q-learning,100,226,0.9800000190734863
Committed Q-learning,100,227,0.9810000061988831
Committed Q-learning,100,228,0.9829999804496765
Committed Q-learning,100,229,0.9829999804496765
Committed Q-learning,100,230,0.9829999804496765
Committed Q-learning,100,231,0.9900000095367432
Committed Q-learning,100,232,0.9890000224113464
Committed Q-learning,100,233,0.9909999966621399
Committed Q-learning,100,234,0.9919999837875366
Committed Q-learning,100,235,0.9929999709129333
Committed Q-learning,100,236,0.9919999837875366
Committed Q-learning,100,237,0.9929999709129333
Committed Q-learning,100,238,0.9940000176429749
Committed Q-learning,100,239,0.9950000047683716
Committed Q-learning,100,240,0.9980000257492065
Committed Q-learning,100,241,0.9980000257492065
Committed Q-learning,100,242,1.0
Committed Q-learning,100,243,1.0
Committed Q-learning,100,244,1.0
Committed Q-learning,100,245,1.0
Committed Q-learning,100,246,1.0
Committed Q-learning,100,247,1.0
Committed Q-learning,100,248,1.0
Committed Q-learning,100,249,1.0
Committed Q-learning,100,250,1.0
Committed Q-learning,100,251,1.0
Committed Q-learning,100,252,1.0
Committed Q-learning,100,253,1.0
Committed Q-learning,100,254,1.0
Committed Q-learning,100,255,1.0
Committed Q-learning,100,256,1.0
Committed Q-learning,100,257,1.0
Committed Q-learning,100,258,1.0
Committed Q-learning,100,259,1.0
Committed Q-learning,100,260,1.0
Committed Q-learning,100,261,1.0
Committed Q-learning,100,262,1.0
Committed Q-learning,100,263,1.0
Committed Q-learning,100,264,1.0
Committed Q-learning,100,265,1.0
Committed Q-learning,100,266,1.0
Committed Q-learning,100,267,1.0
Committed Q-learning,100,268,1.0
Committed Q-learning,100,269,1.0
Committed Q-learning,100,270,1.0
Committed Q-learning,100,271,1.0
Committed Q-learning,100,272,1.0
Committed Q-learning,100,273,1.0
Committed Q-learning,100,274,1.0
Committed Q-learning,100,275,1.0
Committed Q-learning,100,276,1.0
Committed Q-learning,100,277,1.0
Committed Q-learning,100,278,1.0
Committed Q-learning,100,279,1.0
Committed Q-learning,100,280,1.0
Committed Q-learning,100,281,1.0
Committed Q-learning,100,282,1.0
Committed Q-learning,100,283,1.0
Committed Q-learning,100,284,1.0
Committed Q-learning,100,285,1.0
Committed Q-learning,100,286,1.0
Committed Q-learning,100,287,1.0
Committed Q-learning,100,288,1.0
Committed Q-learning,100,289,1.0
Committed Q-learning,100,290,1.0
Committed Q-learning,100,291,1.0
Committed Q-learning,100,292,1.0
Committed Q-learning,100,293,1.0
Committed Q-learning,100,294,1.0
Committed Q-learning,100,295,1.0
Committed Q-learning,100,296,1.0
Committed Q-learning,100,297,1.0
Committed Q-learning,100,298,1.0
Committed Q-learning,100,299,1.0
Committed Q-learning,100,300,1.0
Committed Q-learning,100,301,1.0
Committed Q-learning,100,302,1.0
Committed Q-learning,100,303,1.0
Committed Q-learning,100,304,1.0
Committed Q-learning,100,305,1.0
Committed Q-learning,100,306,1.0
Committed Q-learning,100,307,1.0
Committed Q-learning,100,308,1.0
Committed Q-learning,100,309,1.0
Committed Q-learning,100,310,1.0
Committed Q-learning,100,311,1.0
Committed Q-learning,100,312,1.0
Committed Q-learning,100,313,1.0
Committed Q-learning,100,314,1.0
Committed Q-learning,100,315,1.0
Committed Q-learning,100,316,1.0
Committed Q-learning,100,317,1.0
Committed Q-learning,100,318,1.0
Committed Q-learning,100,319,1.0
Committed Q-learning,100,320,1.0
Committed Q-learning,100,321,1.0
Committed Q-learning,100,322,1.0
Committed Q-learning,100,323,1.0
Committed Q-learning,100,324,1.0
Committed Q-learning,100,325,1.0
Committed Q-learning,100,326,1.0
Committed Q-learning,100,327,1.0
Committed Q-learning,100,328,1.0
Committed Q-learning,100,329,1.0
Committed Q-learning,100,330,1.0
Committed Q-learning,100,331,1.0
Committed Q-learning,100,332,1.0
Committed Q-learning,100,333,1.0
Committed Q-learning,100,334,1.0
Committed Q-learning,100,335,1.0
Committed Q-learning,100,336,1.0
Committed Q-learning,100,337,1.0
Committed Q-learning,100,338,1.0
Committed Q-learning,100,339,1.0
Committed Q-learning,100,340,1.0
Committed Q-learning,100,341,1.0
Committed Q-learning,100,342,1.0
Committed Q-learning,100,343,1.0
Committed Q-learning,100,344,1.0
Committed Q-learning,100,345,1.0
Committed Q-learning,100,346,1.0
Committed Q-learning,100,347,1.0
Committed Q-learning,100,348,1.0
Committed Q-learning,100,349,1.0
Committed Q-learning,100,350,1.0
Committed Q-learning,100,351,1.0
Committed Q-learning,100,352,1.0
Committed Q-learning,100,353,1.0
Committed Q-learning,100,354,1.0
Committed Q-learning,100,355,1.0
Committed Q-learning,100,356,1.0
Committed Q-learning,100,357,1.0
Committed Q-learning,100,358,1.0
Committed Q-learning,100,359,1.0
Committed Q-learning,100,360,1.0
Committed Q-learning,100,361,1.0
Committed Q-learning,100,362,1.0
Committed Q-learning,100,363,1.0
Committed Q-learning,100,364,1.0
Committed Q-learning,100,365,1.0
Committed Q-learning,100,366,1.0
Committed Q-learning,100,367,1.0
Committed Q-learning,100,368,1.0
Committed Q-learning,100,369,1.0
Committed Q-learning,100,370,1.0
Committed Q-learning,100,371,1.0
Committed Q-learning,100,372,1.0
Committed Q-learning,100,373,1.0
Committed Q-learning,100,374,1.0
Committed Q-learning,100,375,1.0
Committed Q-learning,100,376,1.0
Committed Q-learning,100,377,1.0
Committed Q-learning,100,378,1.0
Committed Q-learning,100,379,1.0
Committed Q-learning,100,380,1.0
Committed Q-learning,100,381,1.0
Committed Q-learning,100,382,1.0
Committed Q-learning,100,383,1.0
Committed Q-learning,100,384,1.0
Committed Q-learning,100,385,1.0
Committed Q-learning,100,386,1.0
Committed Q-learning,100,387,1.0
Committed Q-learning,100,388,1.0
Committed Q-learning,100,389,1.0
Committed Q-learning,100,390,1.0
Committed Q-learning,100,391,1.0
Committed Q-learning,100,392,1.0
Committed Q-learning,100,393,1.0
Committed Q-learning,100,394,1.0
Committed Q-learning,100,395,1.0
Committed Q-learning,100,396,1.0
Committed Q-learning,100,397,1.0
Committed Q-learning,100,398,1.0
Committed Q-learning,100,399,1.0
Committed Q-learning,100,400,1.0
Committed Q-learning,100,401,1.0
Committed Q-learning,100,402,1.0
Committed Q-learning,100,403,1.0
Committed Q-learning,100,404,1.0
Committed Q-learning,100,405,1.0
Committed Q-learning,100,406,1.0
Committed Q-learning,100,407,1.0
Committed Q-learning,100,408,1.0
Committed Q-learning,100,409,1.0
Committed Q-learning,100,410,1.0
Committed Q-learning,100,411,1.0
Committed Q-learning,100,412,1.0
Committed Q-learning,100,413,1.0
Committed Q-learning,100,414,1.0
Committed Q-learning,100,415,1.0
Committed Q-learning,100,416,1.0
Committed Q-learning,100,417,1.0
Committed Q-learning,100,418,1.0
Committed Q-learning,100,419,1.0
Committed Q-learning,100,420,1.0
Committed Q-learning,100,421,1.0
Committed Q-learning,100,422,1.0
Committed Q-learning,100,423,1.0
Committed Q-learning,100,424,1.0
Committed Q-learning,100,425,1.0
Committed Q-learning,100,426,1.0
Committed Q-learning,100,427,1.0
Committed Q-learning,100,428,1.0
Committed Q-learning,100,429,1.0
Committed Q-learning,100,430,1.0
Committed Q-learning,100,431,1.0
Committed Q-learning,100,432,1.0
Committed Q-learning,100,433,1.0
Committed Q-learning,100,434,1.0
Committed Q-learning,100,435,1.0
Committed Q-learning,100,436,1.0
Committed Q-learning,100,437,1.0
Committed Q-learning,100,438,1.0
Committed Q-learning,100,439,1.0
Committed Q-learning,100,440,1.0
Committed Q-learning,100,441,1.0
Committed Q-learning,100,442,1.0
Committed Q-learning,100,443,1.0
Committed Q-learning,100,444,1.0
Committed Q-learning,100,445,1.0
Committed Q-learning,100,446,1.0
Committed Q-learning,100,447,1.0
Committed Q-learning,100,448,1.0
Committed Q-learning,100,449,1.0
Committed Q-learning,100,450,1.0
Committed Q-learning,100,451,1.0
Committed Q-learning,100,452,1.0
Committed Q-learning,100,453,1.0
Committed Q-learning,100,454,1.0
Committed Q-learning,100,455,1.0
Committed Q-learning,100,456,1.0
Committed Q-learning,100,457,1.0
Committed Q-learning,100,458,1.0
Committed Q-learning,100,459,1.0
Committed Q-learning,100,460,1.0
Committed Q-learning,100,461,1.0
Committed Q-learning,100,462,1.0
Committed Q-learning,100,463,1.0
Committed Q-learning,100,464,1.0
Committed Q-learning,100,465,1.0
Committed Q-learning,100,466,1.0
Committed Q-learning,100,467,1.0
Committed Q-learning,100,468,1.0
Committed Q-learning,100,469,1.0
Committed Q-learning,100,470,1.0
Committed Q-learning,100,471,1.0
Committed Q-learning,100,472,1.0
Committed Q-learning,100,473,1.0
Committed Q-learning,100,474,1.0
Committed Q-learning,100,475,1.0
Committed Q-learning,100,476,1.0
Committed Q-learning,100,477,1.0
Committed Q-learning,100,478,1.0
Committed Q-learning,100,479,1.0
Committed Q-learning,100,480,1.0
Committed Q-learning,100,481,1.0
Committed Q-learning,100,482,1.0
Committed Q-learning,100,483,1.0
Committed Q-learning,100,484,1.0
Committed Q-learning,100,485,1.0
Committed Q-learning,100,486,1.0
Committed Q-learning,100,487,1.0
Committed Q-learning,100,488,1.0
Committed Q-learning,100,489,1.0
Committed Q-learning,100,490,1.0
Committed Q-learning,100,491,1.0
Committed Q-learning,100,492,1.0
Committed Q-learning,100,493,1.0
Committed Q-learning,100,494,1.0
Committed Q-learning,100,495,1.0
Committed Q-learning,100,496,1.0
Committed Q-learning,100,497,1.0
Committed Q-learning,100,498,1.0
Committed Q-learning,100,499,1.0
Committed Q-learning,100,500,1.0
Committed Q-learning,100,501,1.0
Committed Q-learning,100,502,1.0
Committed Q-learning,100,503,1.0
Committed Q-learning,100,504,1.0
Committed Q-learning,100,505,1.0
Committed Q-learning,100,506,1.0
Committed Q-learning,100,507,1.0
Committed Q-learning,100,508,1.0
Committed Q-learning,100,509,1.0
Committed Q-learning,100,510,1.0
Committed Q-learning,100,511,1.0
Committed Q-learning,100,512,1.0
Committed Q-learning,100,513,1.0
Committed Q-learning,100,514,1.0
Committed Q-learning,100,515,1.0
Committed Q-learning,100,516,1.0
Committed Q-learning,100,517,1.0
Committed Q-learning,100,518,1.0
Committed Q-learning,100,519,1.0
Committed Q-learning,100,520,1.0
Committed Q-learning,100,521,1.0
Committed Q-learning,100,522,1.0
Committed Q-learning,100,523,1.0
Committed Q-learning,100,524,1.0
Committed Q-learning,100,525,1.0
Committed Q-learning,100,526,1.0
Committed Q-learning,100,527,1.0
Committed Q-learning,100,528,1.0
Committed Q-learning,100,529,1.0
Committed Q-learning,100,530,1.0
Committed Q-learning,100,531,1.0
Committed Q-learning,100,532,1.0
Committed Q-learning,100,533,1.0
Committed Q-learning,100,534,1.0
Committed Q-learning,100,535,1.0
Committed Q-learning,100,536,1.0
Committed Q-learning,100,537,1.0
Committed Q-learning,100,538,1.0
Committed Q-learning,100,539,1.0
Committed Q-learning,100,540,1.0
Committed Q-learning,100,541,1.0
Committed Q-learning,100,542,1.0
Committed Q-learning,100,543,1.0
Committed Q-learning,100,544,1.0
Committed Q-learning,100,545,1.0
Committed Q-learning,100,546,1.0
Committed Q-learning,100,547,1.0
Committed Q-learning,100,548,1.0
Committed Q-learning,100,549,1.0
Committed Q-learning,100,550,1.0
Committed Q-learning,100,551,1.0
Committed Q-learning,100,552,1.0
Committed Q-learning,100,553,1.0
Committed Q-learning,100,554,1.0
Committed Q-learning,100,555,1.0
Committed Q-learning,100,556,1.0
Committed Q-learning,100,557,1.0
Committed Q-learning,100,558,1.0
Committed Q-learning,100,559,1.0
Committed Q-learning,100,560,1.0
Committed Q-learning,100,561,1.0
Committed Q-learning,100,562,1.0
Committed Q-learning,100,563,1.0
Committed Q-learning,100,564,1.0
Committed Q-learning,100,565,1.0
Committed Q-learning,100,566,1.0
Committed Q-learning,100,567,1.0
Committed Q-learning,100,568,1.0
Committed Q-learning,100,569,1.0
Committed Q-learning,100,570,1.0
Committed Q-learning,100,571,1.0
Committed Q-learning,100,572,1.0
Committed Q-learning,100,573,1.0
Committed Q-learning,100,574,1.0
Committed Q-learning,100,575,1.0
Committed Q-learning,100,576,1.0
Committed Q-learning,100,577,1.0
Committed Q-learning,100,578,1.0
Committed Q-learning,100,579,1.0
Committed Q-learning,100,580,1.0
Committed Q-learning,100,581,1.0
Committed Q-learning,100,582,1.0
Committed Q-learning,100,583,1.0
Committed Q-learning,100,584,1.0
Committed Q-learning,100,585,1.0
Committed Q-learning,100,586,1.0
Committed Q-learning,100,587,1.0
Committed Q-learning,100,588,1.0
Committed Q-learning,100,589,1.0
Committed Q-learning,100,590,1.0
Committed Q-learning,100,591,1.0
Committed Q-learning,100,592,1.0
Committed Q-learning,100,593,1.0
Committed Q-learning,100,594,1.0
Committed Q-learning,100,595,1.0
Committed Q-learning,100,596,1.0
Committed Q-learning,100,597,1.0
Committed Q-learning,100,598,1.0
Committed Q-learning,100,599,1.0
Committed Q-learning,100,600,1.0
Committed Q-learning,100,601,1.0
Committed Q-learning,100,602,1.0
Committed Q-learning,100,603,1.0
Committed Q-learning,100,604,1.0
Committed Q-learning,100,605,1.0
Committed Q-learning,100,606,1.0
Committed Q-learning,100,607,1.0
Committed Q-learning,100,608,1.0
Committed Q-learning,100,609,1.0
Committed Q-learning,100,610,1.0
Committed Q-learning,100,611,1.0
Committed Q-learning,100,612,1.0
Committed Q-learning,100,613,1.0
Committed Q-learning,100,614,1.0
Committed Q-learning,100,615,1.0
Committed Q-learning,100,616,1.0
Committed Q-learning,100,617,1.0
Committed Q-learning,100,618,1.0
Committed Q-learning,100,619,1.0
Committed Q-learning,100,620,1.0
Committed Q-learning,100,621,1.0
Committed Q-learning,100,622,1.0
Committed Q-learning,100,623,1.0
Committed Q-learning,100,624,1.0
Committed Q-learning,100,625,1.0
Committed Q-learning,100,626,1.0
Committed Q-learning,100,627,1.0
Committed Q-learning,100,628,1.0
Committed Q-learning,100,629,1.0
Committed Q-learning,100,630,1.0
Committed Q-learning,100,631,1.0
Committed Q-learning,100,632,1.0
Committed Q-learning,100,633,1.0
Committed Q-learning,100,634,1.0
Committed Q-learning,100,635,1.0
Committed Q-learning,100,636,1.0
Committed Q-learning,100,637,1.0
Committed Q-learning,100,638,1.0
Committed Q-learning,100,639,1.0
Committed Q-learning,100,640,1.0
Committed Q-learning,100,641,1.0
Committed Q-learning,100,642,1.0
Committed Q-learning,100,643,1.0
Committed Q-learning,100,644,1.0
Committed Q-learning,100,645,1.0
Committed Q-learning,100,646,1.0
Committed Q-learning,100,647,1.0
Committed Q-learning,100,648,1.0
Committed Q-learning,100,649,1.0
Committed Q-learning,100,650,1.0
Committed Q-learning,100,651,1.0
Committed Q-learning,100,652,1.0
Committed Q-learning,100,653,1.0
Committed Q-learning,100,654,1.0
Committed Q-learning,100,655,1.0
Committed Q-learning,100,656,1.0
Committed Q-learning,100,657,1.0
Committed Q-learning,100,658,1.0
Committed Q-learning,100,659,1.0
Committed Q-learning,100,660,1.0
Committed Q-learning,100,661,1.0
Committed Q-learning,100,662,1.0
Committed Q-learning,100,663,1.0
Committed Q-learning,100,664,1.0
Committed Q-learning,100,665,1.0
Committed Q-learning,100,666,1.0
Committed Q-learning,100,667,1.0
Committed Q-learning,100,668,1.0
Committed Q-learning,100,669,1.0
Committed Q-learning,100,670,1.0
Committed Q-learning,100,671,1.0
Committed Q-learning,100,672,1.0
Committed Q-learning,100,673,1.0
Committed Q-learning,100,674,1.0
Committed Q-learning,100,675,1.0
Committed Q-learning,100,676,1.0
Committed Q-learning,100,677,1.0
Committed Q-learning,100,678,1.0
Committed Q-learning,100,679,1.0
Committed Q-learning,100,680,1.0
Committed Q-learning,100,681,1.0
Committed Q-learning,100,682,1.0
Committed Q-learning,100,683,1.0
Committed Q-learning,100,684,1.0
Committed Q-learning,100,685,1.0
Committed Q-learning,100,686,1.0
Committed Q-learning,100,687,1.0
Committed Q-learning,100,688,1.0
Committed Q-learning,100,689,1.0
Committed Q-learning,100,690,1.0
Committed Q-learning,100,691,1.0
Committed Q-learning,100,692,1.0
Committed Q-learning,100,693,1.0
Committed Q-learning,100,694,1.0
Committed Q-learning,100,695,1.0
Committed Q-learning,100,696,1.0
Committed Q-learning,100,697,1.0
Committed Q-learning,100,698,1.0
Committed Q-learning,100,699,1.0
Committed Q-learning,100,700,1.0
Committed Q-learning,100,701,1.0
Committed Q-learning,100,702,1.0
Committed Q-learning,100,703,1.0
Committed Q-learning,100,704,1.0
Committed Q-learning,100,705,1.0
Committed Q-learning,100,706,1.0
Committed Q-learning,100,707,1.0
Committed Q-learning,100,708,1.0
Committed Q-learning,100,709,1.0
Committed Q-learning,100,710,1.0
Committed Q-learning,100,711,1.0
Committed Q-learning,100,712,1.0
Committed Q-learning,100,713,1.0
Committed Q-learning,100,714,1.0
Committed Q-learning,100,715,1.0
Committed Q-learning,100,716,1.0
Committed Q-learning,100,717,1.0
Committed Q-learning,100,718,1.0
Committed Q-learning,100,719,1.0
Committed Q-learning,100,720,1.0
Committed Q-learning,100,721,1.0
Committed Q-learning,100,722,1.0
Committed Q-learning,100,723,1.0
Committed Q-learning,100,724,1.0
Committed Q-learning,100,725,1.0
Committed Q-learning,100,726,1.0
Committed Q-learning,100,727,1.0
Committed Q-learning,100,728,1.0
Committed Q-learning,100,729,1.0
Committed Q-learning,100,730,1.0
Committed Q-learning,100,731,1.0
Committed Q-learning,100,732,1.0
Committed Q-learning,100,733,1.0
Committed Q-learning,100,734,1.0
Committed Q-learning,100,735,1.0
Committed Q-learning,100,736,1.0
Committed Q-learning,100,737,1.0
Committed Q-learning,100,738,1.0
Committed Q-learning,100,739,1.0
Committed Q-learning,100,740,1.0
Committed Q-learning,100,741,1.0
Committed Q-learning,100,742,1.0
Committed Q-learning,100,743,1.0
Committed Q-learning,100,744,1.0
Committed Q-learning,100,745,1.0
Committed Q-learning,100,746,1.0
Committed Q-learning,100,747,1.0
Committed Q-learning,100,748,1.0
Committed Q-learning,100,749,1.0
Committed Q-learning,100,750,1.0
Committed Q-learning,100,751,1.0
Committed Q-learning,100,752,1.0
Committed Q-learning,100,753,1.0
Committed Q-learning,100,754,1.0
Committed Q-learning,100,755,1.0
Committed Q-learning,100,756,1.0
Committed Q-learning,100,757,1.0
Committed Q-learning,100,758,1.0
Committed Q-learning,100,759,1.0
Committed Q-learning,100,760,1.0
Committed Q-learning,100,761,1.0
Committed Q-learning,100,762,1.0
Committed Q-learning,100,763,1.0
Committed Q-learning,100,764,1.0
Committed Q-learning,100,765,1.0
Committed Q-learning,100,766,1.0
Committed Q-learning,100,767,1.0
Committed Q-learning,100,768,1.0
Committed Q-learning,100,769,1.0
Committed Q-learning,100,770,1.0
Committed Q-learning,100,771,1.0
Committed Q-learning,100,772,1.0
Committed Q-learning,100,773,1.0
Committed Q-learning,100,774,1.0
Committed Q-learning,100,775,1.0
Committed Q-learning,100,776,1.0
Committed Q-learning,100,777,1.0
Committed Q-learning,100,778,1.0
Committed Q-learning,100,779,1.0
Committed Q-learning,100,780,1.0
Committed Q-learning,100,781,1.0
Committed Q-learning,100,782,1.0
Committed Q-learning,100,783,1.0
Committed Q-learning,100,784,1.0
Committed Q-learning,100,785,1.0
Committed Q-learning,100,786,1.0
Committed Q-learning,100,787,1.0
Committed Q-learning,100,788,1.0
Committed Q-learning,100,789,1.0
Committed Q-learning,100,790,1.0
Committed Q-learning,100,791,1.0
Committed Q-learning,100,792,1.0
Committed Q-learning,100,793,1.0
Committed Q-learning,100,794,1.0
Committed Q-learning,100,795,1.0
Committed Q-learning,100,796,1.0
Committed Q-learning,100,797,1.0
Committed Q-learning,100,798,1.0
Committed Q-learning,100,799,1.0
Committed Q-learning,100,800,1.0
Committed Q-learning,100,801,1.0
Committed Q-learning,100,802,1.0
Committed Q-learning,100,803,1.0
Committed Q-learning,100,804,1.0
Committed Q-learning,100,805,1.0
Committed Q-learning,100,806,1.0
Committed Q-learning,100,807,1.0
Committed Q-learning,100,808,1.0
Committed Q-learning,100,809,1.0
Committed Q-learning,100,810,1.0
Committed Q-learning,100,811,1.0
Committed Q-learning,100,812,1.0
Committed Q-learning,100,813,1.0
Committed Q-learning,100,814,1.0
Committed Q-learning,100,815,1.0
Committed Q-learning,100,816,1.0
Committed Q-learning,100,817,1.0
Committed Q-learning,100,818,1.0
Committed Q-learning,100,819,1.0
Committed Q-learning,100,820,1.0
Committed Q-learning,100,821,1.0
Committed Q-learning,100,822,1.0
Committed Q-learning,100,823,1.0
Committed Q-learning,100,824,1.0
Committed Q-learning,100,825,1.0
Committed Q-learning,100,826,1.0
Committed Q-learning,100,827,1.0
Committed Q-learning,100,828,1.0
Committed Q-learning,100,829,1.0
Committed Q-learning,100,830,1.0
Committed Q-learning,100,831,1.0
Committed Q-learning,100,832,1.0
Committed Q-learning,100,833,1.0
Committed Q-learning,100,834,1.0
Committed Q-learning,100,835,1.0
Committed Q-learning,100,836,1.0
Committed Q-learning,100,837,1.0
Committed Q-learning,100,838,1.0
Committed Q-learning,100,839,1.0
Committed Q-learning,100,840,1.0
Committed Q-learning,100,841,1.0
Committed Q-learning,100,842,1.0
Committed Q-learning,100,843,1.0
Committed Q-learning,100,844,1.0
Committed Q-learning,100,845,1.0
Committed Q-learning,100,846,1.0
Committed Q-learning,100,847,1.0
Committed Q-learning,100,848,1.0
Committed Q-learning,100,849,1.0
Committed Q-learning,100,850,1.0
Committed Q-learning,100,851,1.0
Committed Q-learning,100,852,1.0
Committed Q-learning,100,853,1.0
Committed Q-learning,100,854,1.0
Committed Q-learning,100,855,1.0
Committed Q-learning,100,856,1.0
Committed Q-learning,100,857,1.0
Committed Q-learning,100,858,1.0
Committed Q-learning,100,859,1.0
Committed Q-learning,100,860,1.0
Committed Q-learning,100,861,1.0
Committed Q-learning,100,862,1.0
Committed Q-learning,100,863,1.0
Committed Q-learning,100,864,1.0
Committed Q-learning,100,865,1.0
Committed Q-learning,100,866,1.0
Committed Q-learning,100,867,1.0
Committed Q-learning,100,868,1.0
Committed Q-learning,100,869,1.0
Committed Q-learning,100,870,1.0
Committed Q-learning,100,871,1.0
Committed Q-learning,100,872,1.0
Committed Q-learning,100,873,1.0
Committed Q-learning,100,874,1.0
Committed Q-learning,100,875,1.0
Committed Q-learning,100,876,1.0
Committed Q-learning,100,877,1.0
Committed Q-learning,100,878,1.0
Committed Q-learning,100,879,1.0
Committed Q-learning,100,880,1.0
Committed Q-learning,100,881,1.0
Committed Q-learning,100,882,1.0
Committed Q-learning,100,883,1.0
Committed Q-learning,100,884,1.0
Committed Q-learning,100,885,1.0
Committed Q-learning,100,886,1.0
Committed Q-learning,100,887,1.0
Committed Q-learning,100,888,1.0
Committed Q-learning,100,889,1.0
Committed Q-learning,100,890,1.0
Committed Q-learning,100,891,1.0
Committed Q-learning,100,892,1.0
Committed Q-learning,100,893,1.0
Committed Q-learning,100,894,1.0
Committed Q-learning,100,895,1.0
Committed Q-learning,100,896,1.0
Committed Q-learning,100,897,1.0
Committed Q-learning,100,898,1.0
Committed Q-learning,100,899,1.0
Committed Q-learning,100,900,1.0
Committed Q-learning,100,901,1.0
Committed Q-learning,100,902,1.0
Committed Q-learning,100,903,1.0
Committed Q-learning,100,904,1.0
Committed Q-learning,100,905,1.0
Committed Q-learning,100,906,1.0
Committed Q-learning,100,907,1.0
Committed Q-learning,100,908,1.0
Committed Q-learning,100,909,1.0
Committed Q-learning,100,910,1.0
Committed Q-learning,100,911,1.0
Committed Q-learning,100,912,1.0
Committed Q-learning,100,913,1.0
Committed Q-learning,100,914,1.0
Committed Q-learning,100,915,1.0
Committed Q-learning,100,916,1.0
Committed Q-learning,100,917,1.0
Committed Q-learning,100,918,1.0
Committed Q-learning,100,919,1.0
Committed Q-learning,100,920,1.0
Committed Q-learning,100,921,1.0
Committed Q-learning,100,922,1.0
Committed Q-learning,100,923,1.0
Committed Q-learning,100,924,1.0
Committed Q-learning,100,925,1.0
Committed Q-learning,100,926,1.0
Committed Q-learning,100,927,1.0
Committed Q-learning,100,928,1.0
Committed Q-learning,100,929,1.0
Committed Q-learning,100,930,1.0
Committed Q-learning,100,931,1.0
Committed Q-learning,100,932,1.0
Committed Q-learning,100,933,1.0
Committed Q-learning,100,934,1.0
Committed Q-learning,100,935,1.0
Committed Q-learning,100,936,1.0
Committed Q-learning,100,937,1.0
Committed Q-learning,100,938,1.0
Committed Q-learning,100,939,1.0
Committed Q-learning,100,940,1.0
Committed Q-learning,100,941,1.0
Committed Q-learning,100,942,1.0
Committed Q-learning,100,943,1.0
Committed Q-learning,100,944,1.0
Committed Q-learning,100,945,1.0
Committed Q-learning,100,946,1.0
Committed Q-learning,100,947,1.0
Committed Q-learning,100,948,1.0
Committed Q-learning,100,949,1.0
Committed Q-learning,100,950,1.0
Committed Q-learning,100,951,1.0
Committed Q-learning,100,952,1.0
Committed Q-learning,100,953,1.0
Committed Q-learning,100,954,1.0
Committed Q-learning,100,955,1.0
Committed Q-learning,100,956,1.0
Committed Q-learning,100,957,1.0
Committed Q-learning,100,958,1.0
Committed Q-learning,100,959,1.0
Committed Q-learning,100,960,1.0
Committed Q-learning,100,961,1.0
Committed Q-learning,100,962,1.0
Committed Q-learning,100,963,1.0
Committed Q-learning,100,964,1.0
Committed Q-learning,100,965,1.0
Committed Q-learning,100,966,1.0
Committed Q-learning,100,967,1.0
Committed Q-learning,100,968,1.0
Committed Q-learning,100,969,1.0
Committed Q-learning,100,970,1.0
Committed Q-learning,100,971,1.0
Committed Q-learning,100,972,1.0
Committed Q-learning,100,973,1.0
Committed Q-learning,100,974,1.0
Committed Q-learning,100,975,1.0
Committed Q-learning,100,976,1.0
Committed Q-learning,100,977,1.0
Committed Q-learning,100,978,1.0
Committed Q-learning,100,979,1.0
Committed Q-learning,100,980,1.0
Committed Q-learning,100,981,1.0
Committed Q-learning,100,982,1.0
Committed Q-learning,100,983,1.0
Committed Q-learning,100,984,1.0
Committed Q-learning,100,985,1.0
Committed Q-learning,100,986,1.0
Committed Q-learning,100,987,1.0
Committed Q-learning,100,988,1.0
Committed Q-learning,100,989,1.0
Committed Q-learning,100,990,1.0
Committed Q-learning,100,991,1.0
Committed Q-learning,100,992,1.0
Committed Q-learning,100,993,1.0
Committed Q-learning,100,994,1.0
Committed Q-learning,100,995,1.0
Committed Q-learning,100,996,1.0
Committed Q-learning,100,997,1.0
Committed Q-learning,100,998,1.0
Committed Q-learning,100,999,1.0
Committed Q-learning,100,1000,1.0
Committed Q-learning,200,1,0.2290000021457672
Committed Q-learning,200,2,0.17000000178813934
Committed Q-learning,200,3,0.09799999743700027
Committed Q-learning,200,4,0.06300000101327896
Committed Q-learning,200,5,0.032999999821186066
Committed Q-learning,200,6,0.014999999664723873
Committed Q-learning,200,7,0.017999999225139618
Committed Q-learning,200,8,0.017000000923871994
Committed Q-learning,200,9,0.014999999664723873
Committed Q-learning,200,10,0.01899999938905239
Committed Q-learning,200,11,0.01600000075995922
Committed Q-learning,200,12,0.017000000923871994
Committed Q-learning,200,13,0.02500000037252903
Committed Q-learning,200,14,0.01899999938905239
Committed Q-learning,200,15,0.017000000923871994
Committed Q-learning,200,16,0.012000000104308128
Committed Q-learning,200,17,0.01899999938905239
Committed Q-learning,200,18,0.01600000075995922
Committed Q-learning,200,19,0.017999999225139618
Committed Q-learning,200,20,0.014000000432133675
Committed Q-learning,200,21,0.014999999664723873
Committed Q-learning,200,22,0.009999999776482582
Committed Q-learning,200,23,0.00800000037997961
Committed Q-learning,200,24,0.00800000037997961
Committed Q-learning,200,25,0.00800000037997961
Committed Q-learning,200,26,0.003000000026077032
Committed Q-learning,200,27,0.004999999888241291
Committed Q-learning,200,28,0.003000000026077032
Committed Q-learning,200,29,0.004000000189989805
Committed Q-learning,200,30,0.004999999888241291
Committed Q-learning,200,31,0.003000000026077032
Committed Q-learning,200,32,0.003000000026077032
Committed Q-learning,200,33,0.0010000000474974513
Committed Q-learning,200,34,0.0010000000474974513
Committed Q-learning,200,35,0.0010000000474974513
Committed Q-learning,200,36,0.0020000000949949026
Committed Q-learning,200,37,0.0
Committed Q-learning,200,38,0.0020000000949949026
Committed Q-learning,200,39,0.0
Committed Q-learning,200,40,0.0
Committed Q-learning,200,41,0.0
Committed Q-learning,200,42,0.0
Committed Q-learning,200,43,0.0
Committed Q-learning,200,44,0.0
Committed Q-learning,200,45,0.0
Committed Q-learning,200,46,0.0
Committed Q-learning,200,47,0.0
Committed Q-learning,200,48,0.0
Committed Q-learning,200,49,0.0
Committed Q-learning,200,50,0.0
Committed Q-learning,200,51,0.0
Committed Q-learning,200,52,0.0
Committed Q-learning,200,53,0.0
Committed Q-learning,200,54,0.0
Committed Q-learning,200,55,0.0
Committed Q-learning,200,56,0.0
Committed Q-learning,200,57,0.0
Committed Q-learning,200,58,0.0
Committed Q-learning,200,59,0.0
Committed Q-learning,200,60,0.0
Committed Q-learning,200,61,0.0
Committed Q-learning,200,62,0.0
Committed Q-learning,200,63,0.0
Committed Q-learning,200,64,0.0
Committed Q-learning,200,65,0.0
Committed Q-learning,200,66,0.0
Committed Q-learning,200,67,0.0
Committed Q-learning,200,68,0.0
Committed Q-learning,200,69,0.0
Committed Q-learning,200,70,0.0
Committed Q-learning,200,71,0.0
Committed Q-learning,200,72,0.0
Committed Q-learning,200,73,0.0
Committed Q-learning,200,74,0.0
Committed Q-learning,200,75,0.0
Committed Q-learning,200,76,0.0
Committed Q-learning,200,77,0.0
Committed Q-learning,200,78,0.0
Committed Q-learning,200,79,0.0
Committed Q-learning,200,80,0.0
Committed Q-learning,200,81,0.0
Committed Q-learning,200,82,0.0
Committed Q-learning,200,83,0.0
Committed Q-learning,200,84,0.0
Committed Q-learning,200,85,0.0
Committed Q-learning,200,86,0.0
Committed Q-learning,200,87,0.0
Committed Q-learning,200,88,0.0
Committed Q-learning,200,89,0.0
Committed Q-learning,200,90,0.0
Committed Q-learning,200,91,0.0
Committed Q-learning,200,92,0.0
Committed Q-learning,200,93,0.0
Committed Q-learning,200,94,0.0
Committed Q-learning,200,95,0.0
Committed Q-learning,200,96,0.0
Committed Q-learning,200,97,0.0
Committed Q-learning,200,98,0.0
Committed Q-learning,200,99,0.0
Committed Q-learning,200,100,0.0
Committed Q-learning,200,101,0.0
Committed Q-learning,200,102,0.0
Committed Q-learning,200,103,0.0
Committed Q-learning,200,104,0.0
Committed Q-learning,200,105,0.0
Committed Q-learning,200,106,0.0
Committed Q-learning,200,107,0.0
Committed Q-learning,200,108,0.0
Committed Q-learning,200,109,0.0
Committed Q-learning,200,110,0.0
Committed Q-learning,200,111,0.0
Committed Q-learning,200,112,0.0
Committed Q-learning,200,113,0.0
Committed Q-learning,200,114,0.0
Committed Q-learning,200,115,0.0
Committed Q-learning,200,116,0.0
Committed Q-learning,200,117,0.0
Committed Q-learning,200,118,0.0
Committed Q-learning,200,119,0.0
Committed Q-learning,200,120,0.0
Committed Q-learning,200,121,0.0
Committed Q-learning,200,122,0.0
Committed Q-learning,200,123,0.0
Committed Q-learning,200,124,0.0
Committed Q-learning,200,125,0.0
Committed Q-learning,200,126,0.0
Committed Q-learning,200,127,0.0
Committed Q-learning,200,128,0.0
Committed Q-learning,200,129,0.0
Committed Q-learning,200,130,0.0
Committed Q-learning,200,131,0.0
Committed Q-learning,200,132,0.0
Committed Q-learning,200,133,0.0
Committed Q-learning,200,134,0.0
Committed Q-learning,200,135,0.0
Committed Q-learning,200,136,0.0
Committed Q-learning,200,137,0.0
Committed Q-learning,200,138,0.0
Committed Q-learning,200,139,0.0
Committed Q-learning,200,140,0.0
Committed Q-learning,200,141,0.0
Committed Q-learning,200,142,0.0
Committed Q-learning,200,143,0.0
Committed Q-learning,200,144,0.0
Committed Q-learning,200,145,0.0
Committed Q-learning,200,146,0.0
Committed Q-learning,200,147,0.0
Committed Q-learning,200,148,0.0
Committed Q-learning,200,149,0.0
Committed Q-learning,200,150,0.0
Committed Q-learning,200,151,0.0
Committed Q-learning,200,152,0.0
Committed Q-learning,200,153,0.0
Committed Q-learning,200,154,0.0
Committed Q-learning,200,155,0.0
Committed Q-learning,200,156,0.0
Committed Q-learning,200,157,0.0
Committed Q-learning,200,158,0.0
Committed Q-learning,200,159,0.0
Committed Q-learning,200,160,0.0
Committed Q-learning,200,161,0.0
Committed Q-learning,200,162,0.0
Committed Q-learning,200,163,0.0
Committed Q-learning,200,164,0.0
Committed Q-learning,200,165,0.0
Committed Q-learning,200,166,0.0
Committed Q-learning,200,167,0.0
Committed Q-learning,200,168,0.0
Committed Q-learning,200,169,0.0
Committed Q-learning,200,170,0.0
Committed Q-learning,200,171,0.0
Committed Q-learning,200,172,0.0
Committed Q-learning,200,173,0.0
Committed Q-learning,200,174,0.0
Committed Q-learning,200,175,0.0
Committed Q-learning,200,176,0.0
Committed Q-learning,200,177,0.0
Committed Q-learning,200,178,0.0
Committed Q-learning,200,179,0.0
Committed Q-learning,200,180,0.0
Committed Q-learning,200,181,0.0
Committed Q-learning,200,182,0.0
Committed Q-learning,200,183,0.0
Committed Q-learning,200,184,0.0
Committed Q-learning,200,185,0.0
Committed Q-learning,200,186,0.0
Committed Q-learning,200,187,0.0
Committed Q-learning,200,188,0.0
Committed Q-learning,200,189,0.0
Committed Q-learning,200,190,0.0
Committed Q-learning,200,191,0.0
Committed Q-learning,200,192,0.0
Committed Q-learning,200,193,0.0
Committed Q-learning,200,194,0.0
Committed Q-learning,200,195,0.0
Committed Q-learning,200,196,0.0
Committed Q-learning,200,197,0.0
Committed Q-learning,200,198,0.0
Committed Q-learning,200,199,0.0
Committed Q-learning,200,200,0.0
Committed Q-learning,200,201,0.05999999865889549
Committed Q-learning,200,202,0.19099999964237213
Committed Q-learning,200,203,0.2669999897480011
Committed Q-learning,200,204,0.32600000500679016
Committed Q-learning,200,205,0.3919999897480011
Committed Q-learning,200,206,0.45100000500679016
Committed Q-learning,200,207,0.5
Committed Q-learning,200,208,0.5519999861717224
Committed Q-learning,200,209,0.5910000205039978
Committed Q-learning,200,210,0.6230000257492065
Committed Q-learning,200,211,0.6510000228881836
Committed Q-learning,200,212,0.6740000247955322
Committed Q-learning,200,213,0.7110000252723694
Committed Q-learning,200,214,0.734000027179718
Committed Q-learning,200,215,0.7590000033378601
Committed Q-learning,200,216,0.7770000100135803
Committed Q-learning,200,217,0.7979999780654907
Committed Q-learning,200,218,0.8169999718666077
Committed Q-learning,200,219,0.8360000252723694
Committed Q-learning,200,220,0.8600000143051147
Committed Q-learning,200,221,0.8790000081062317
Committed Q-learning,200,222,0.890999972820282
Committed Q-learning,200,223,0.9039999842643738
Committed Q-learning,200,224,0.9179999828338623
Committed Q-learning,200,225,0.9300000071525574
Committed Q-learning,200,226,0.9390000104904175
Committed Q-learning,200,227,0.9480000138282776
Committed Q-learning,200,228,0.9559999704360962
Committed Q-learning,200,229,0.9620000123977661
Committed Q-learning,200,230,0.9670000076293945
Committed Q-learning,200,231,0.9700000286102295
Committed Q-learning,200,232,0.9760000109672546
Committed Q-learning,200,233,0.9789999723434448
Committed Q-learning,200,234,0.9819999933242798
Committed Q-learning,200,235,0.9829999804496765
Committed Q-learning,200,236,0.984000027179718
Committed Q-learning,200,237,0.9869999885559082
Committed Q-learning,200,238,0.9869999885559082
Committed Q-learning,200,239,0.9869999885559082
Committed Q-learning,200,240,0.9900000095367432
Committed Q-learning,200,241,0.9919999837875366
Committed Q-learning,200,242,0.9929999709129333
Committed Q-learning,200,243,0.9929999709129333
Committed Q-learning,200,244,0.9929999709129333
Committed Q-learning,200,245,0.9929999709129333
Committed Q-learning,200,246,0.9929999709129333
Committed Q-learning,200,247,0.9929999709129333
Committed Q-learning,200,248,0.9929999709129333
Committed Q-learning,200,249,0.9929999709129333
Committed Q-learning,200,250,0.9929999709129333
Committed Q-learning,200,251,0.9929999709129333
Committed Q-learning,200,252,0.9929999709129333
Committed Q-learning,200,253,0.9929999709129333
Committed Q-learning,200,254,0.9929999709129333
Committed Q-learning,200,255,0.9929999709129333
Committed Q-learning,200,256,0.9929999709129333
Committed Q-learning,200,257,0.9929999709129333
Committed Q-learning,200,258,0.9929999709129333
Committed Q-learning,200,259,0.9929999709129333
Committed Q-learning,200,260,0.9929999709129333
Committed Q-learning,200,261,0.9929999709129333
Committed Q-learning,200,262,0.9929999709129333
Committed Q-learning,200,263,0.9929999709129333
Committed Q-learning,200,264,0.9929999709129333
Committed Q-learning,200,265,0.9929999709129333
Committed Q-learning,200,266,0.9929999709129333
Committed Q-learning,200,267,0.9929999709129333
Committed Q-learning,200,268,0.9929999709129333
Committed Q-learning,200,269,0.9929999709129333
Committed Q-learning,200,270,0.9929999709129333
Committed Q-learning,200,271,0.9929999709129333
Committed Q-learning,200,272,0.9929999709129333
Committed Q-learning,200,273,0.9929999709129333
Committed Q-learning,200,274,0.9929999709129333
Committed Q-learning,200,275,0.9929999709129333
Committed Q-learning,200,276,0.9929999709129333
Committed Q-learning,200,277,0.9929999709129333
Committed Q-learning,200,278,0.9929999709129333
Committed Q-learning,200,279,0.9929999709129333
Committed Q-learning,200,280,0.9929999709129333
Committed Q-learning,200,281,0.9929999709129333
Committed Q-learning,200,282,0.9929999709129333
Committed Q-learning,200,283,0.9929999709129333
Committed Q-learning,200,284,0.9929999709129333
Committed Q-learning,200,285,0.9929999709129333
Committed Q-learning,200,286,0.9929999709129333
Committed Q-learning,200,287,0.9929999709129333
Committed Q-learning,200,288,0.9929999709129333
Committed Q-learning,200,289,0.9929999709129333
Committed Q-learning,200,290,0.9929999709129333
Committed Q-learning,200,291,0.9929999709129333
Committed Q-learning,200,292,0.9929999709129333
Committed Q-learning,200,293,0.9929999709129333
Committed Q-learning,200,294,0.9929999709129333
Committed Q-learning,200,295,0.9929999709129333
Committed Q-learning,200,296,0.9929999709129333
Committed Q-learning,200,297,0.9929999709129333
Committed Q-learning,200,298,0.9929999709129333
Committed Q-learning,200,299,0.9929999709129333
Committed Q-learning,200,300,0.9929999709129333
Committed Q-learning,200,301,0.9929999709129333
Committed Q-learning,200,302,0.9929999709129333
Committed Q-learning,200,303,0.9929999709129333
Committed Q-learning,200,304,0.9929999709129333
Committed Q-learning,200,305,0.9929999709129333
Committed Q-learning,200,306,0.9929999709129333
Committed Q-learning,200,307,0.9929999709129333
Committed Q-learning,200,308,0.9929999709129333
Committed Q-learning,200,309,0.9929999709129333
Committed Q-learning,200,310,0.9929999709129333
Committed Q-learning,200,311,0.9929999709129333
Committed Q-learning,200,312,0.9929999709129333
Committed Q-learning,200,313,0.9929999709129333
Committed Q-learning,200,314,0.9929999709129333
Committed Q-learning,200,315,0.9929999709129333
Committed Q-learning,200,316,0.9929999709129333
Committed Q-learning,200,317,0.9929999709129333
Committed Q-learning,200,318,0.9929999709129333
Committed Q-learning,200,319,0.9929999709129333
Committed Q-learning,200,320,0.9929999709129333
Committed Q-learning,200,321,0.9929999709129333
Committed Q-learning,200,322,0.9929999709129333
Committed Q-learning,200,323,0.9929999709129333
Committed Q-learning,200,324,0.9929999709129333
Committed Q-learning,200,325,0.9929999709129333
Committed Q-learning,200,326,0.9929999709129333
Committed Q-learning,200,327,0.9929999709129333
Committed Q-learning,200,328,0.9929999709129333
Committed Q-learning,200,329,0.9929999709129333
Committed Q-learning,200,330,0.9929999709129333
Committed Q-learning,200,331,0.9929999709129333
Committed Q-learning,200,332,0.9929999709129333
Committed Q-learning,200,333,0.9929999709129333
Committed Q-learning,200,334,0.9929999709129333
Committed Q-learning,200,335,0.9929999709129333
Committed Q-learning,200,336,0.9929999709129333
Committed Q-learning,200,337,0.9929999709129333
Committed Q-learning,200,338,0.9929999709129333
Committed Q-learning,200,339,0.9929999709129333
Committed Q-learning,200,340,0.9929999709129333
Committed Q-learning,200,341,0.9929999709129333
Committed Q-learning,200,342,0.9929999709129333
Committed Q-learning,200,343,0.9929999709129333
Committed Q-learning,200,344,0.9929999709129333
Committed Q-learning,200,345,0.9929999709129333
Committed Q-learning,200,346,0.9929999709129333
Committed Q-learning,200,347,0.9929999709129333
Committed Q-learning,200,348,0.9929999709129333
Committed Q-learning,200,349,0.9929999709129333
Committed Q-learning,200,350,0.9929999709129333
Committed Q-learning,200,351,0.9929999709129333
Committed Q-learning,200,352,0.9929999709129333
Committed Q-learning,200,353,0.9929999709129333
Committed Q-learning,200,354,0.9929999709129333
Committed Q-learning,200,355,0.9929999709129333
Committed Q-learning,200,356,0.9929999709129333
Committed Q-learning,200,357,0.9929999709129333
Committed Q-learning,200,358,0.9929999709129333
Committed Q-learning,200,359,0.9929999709129333
Committed Q-learning,200,360,0.9929999709129333
Committed Q-learning,200,361,0.9929999709129333
Committed Q-learning,200,362,0.9929999709129333
Committed Q-learning,200,363,0.9929999709129333
Committed Q-learning,200,364,0.9929999709129333
Committed Q-learning,200,365,0.9929999709129333
Committed Q-learning,200,366,0.9929999709129333
Committed Q-learning,200,367,0.9929999709129333
Committed Q-learning,200,368,0.9929999709129333
Committed Q-learning,200,369,0.9929999709129333
Committed Q-learning,200,370,0.9929999709129333
Committed Q-learning,200,371,0.9929999709129333
Committed Q-learning,200,372,0.9929999709129333
Committed Q-learning,200,373,0.9929999709129333
Committed Q-learning,200,374,0.9929999709129333
Committed Q-learning,200,375,0.9929999709129333
Committed Q-learning,200,376,0.9929999709129333
Committed Q-learning,200,377,0.9929999709129333
Committed Q-learning,200,378,0.9929999709129333
Committed Q-learning,200,379,0.9929999709129333
Committed Q-learning,200,380,0.9929999709129333
Committed Q-learning,200,381,0.9929999709129333
Committed Q-learning,200,382,0.9929999709129333
Committed Q-learning,200,383,0.9929999709129333
Committed Q-learning,200,384,0.9929999709129333
Committed Q-learning,200,385,0.9929999709129333
Committed Q-learning,200,386,0.9929999709129333
Committed Q-learning,200,387,0.9929999709129333
Committed Q-learning,200,388,0.9929999709129333
Committed Q-learning,200,389,0.9929999709129333
Committed Q-learning,200,390,0.9929999709129333
Committed Q-learning,200,391,0.9929999709129333
Committed Q-learning,200,392,0.9929999709129333
Committed Q-learning,200,393,0.9929999709129333
Committed Q-learning,200,394,0.9929999709129333
Committed Q-learning,200,395,0.9929999709129333
Committed Q-learning,200,396,0.9929999709129333
Committed Q-learning,200,397,0.9929999709129333
Committed Q-learning,200,398,0.9929999709129333
Committed Q-learning,200,399,0.9929999709129333
Committed Q-learning,200,400,0.9929999709129333
Committed Q-learning,200,401,0.9929999709129333
Committed Q-learning,200,402,0.9929999709129333
Committed Q-learning,200,403,0.9929999709129333
Committed Q-learning,200,404,0.9950000047683716
Committed Q-learning,200,405,0.9959999918937683
Committed Q-learning,200,406,0.9959999918937683
Committed Q-learning,200,407,0.996999979019165
Committed Q-learning,200,408,0.996999979019165
Committed Q-learning,200,409,0.9980000257492065
Committed Q-learning,200,410,0.9980000257492065
Committed Q-learning,200,411,0.9990000128746033
Committed Q-learning,200,412,0.9990000128746033
Committed Q-learning,200,413,0.9990000128746033
Committed Q-learning,200,414,0.9990000128746033
Committed Q-learning,200,415,0.9990000128746033
Committed Q-learning,200,416,1.0
Committed Q-learning,200,417,1.0
Committed Q-learning,200,418,1.0
Committed Q-learning,200,419,1.0
Committed Q-learning,200,420,1.0
Committed Q-learning,200,421,1.0
Committed Q-learning,200,422,1.0
Committed Q-learning,200,423,1.0
Committed Q-learning,200,424,1.0
Committed Q-learning,200,425,1.0
Committed Q-learning,200,426,1.0
Committed Q-learning,200,427,1.0
Committed Q-learning,200,428,1.0
Committed Q-learning,200,429,1.0
Committed Q-learning,200,430,1.0
Committed Q-learning,200,431,1.0
Committed Q-learning,200,432,1.0
Committed Q-learning,200,433,1.0
Committed Q-learning,200,434,1.0
Committed Q-learning,200,435,1.0
Committed Q-learning,200,436,1.0
Committed Q-learning,200,437,1.0
Committed Q-learning,200,438,1.0
Committed Q-learning,200,439,1.0
Committed Q-learning,200,440,1.0
Committed Q-learning,200,441,1.0
Committed Q-learning,200,442,1.0
Committed Q-learning,200,443,1.0
Committed Q-learning,200,444,1.0
Committed Q-learning,200,445,1.0
Committed Q-learning,200,446,1.0
Committed Q-learning,200,447,1.0
Committed Q-learning,200,448,1.0
Committed Q-learning,200,449,1.0
Committed Q-learning,200,450,1.0
Committed Q-learning,200,451,1.0
Committed Q-learning,200,452,1.0
Committed Q-learning,200,453,1.0
Committed Q-learning,200,454,1.0
Committed Q-learning,200,455,1.0
Committed Q-learning,200,456,1.0
Committed Q-learning,200,457,1.0
Committed Q-learning,200,458,1.0
Committed Q-learning,200,459,1.0
Committed Q-learning,200,460,1.0
Committed Q-learning,200,461,1.0
Committed Q-learning,200,462,1.0
Committed Q-learning,200,463,1.0
Committed Q-learning,200,464,1.0
Committed Q-learning,200,465,1.0
Committed Q-learning,200,466,1.0
Committed Q-learning,200,467,1.0
Committed Q-learning,200,468,1.0
Committed Q-learning,200,469,1.0
Committed Q-learning,200,470,1.0
Committed Q-learning,200,471,1.0
Committed Q-learning,200,472,1.0
Committed Q-learning,200,473,1.0
Committed Q-learning,200,474,1.0
Committed Q-learning,200,475,1.0
Committed Q-learning,200,476,1.0
Committed Q-learning,200,477,1.0
Committed Q-learning,200,478,1.0
Committed Q-learning,200,479,1.0
Committed Q-learning,200,480,1.0
Committed Q-learning,200,481,1.0
Committed Q-learning,200,482,1.0
Committed Q-learning,200,483,1.0
Committed Q-learning,200,484,1.0
Committed Q-learning,200,485,1.0
Committed Q-learning,200,486,1.0
Committed Q-learning,200,487,1.0
Committed Q-learning,200,488,1.0
Committed Q-learning,200,489,1.0
Committed Q-learning,200,490,1.0
Committed Q-learning,200,491,1.0
Committed Q-learning,200,492,1.0
Committed Q-learning,200,493,1.0
Committed Q-learning,200,494,1.0
Committed Q-learning,200,495,1.0
Committed Q-learning,200,496,1.0
Committed Q-learning,200,497,1.0
Committed Q-learning,200,498,1.0
Committed Q-learning,200,499,1.0
Committed Q-learning,200,500,1.0
Committed Q-learning,200,501,1.0
Committed Q-learning,200,502,1.0
Committed Q-learning,200,503,1.0
Committed Q-learning,200,504,1.0
Committed Q-learning,200,505,1.0
Committed Q-learning,200,506,1.0
Committed Q-learning,200,507,1.0
Committed Q-learning,200,508,1.0
Committed Q-learning,200,509,1.0
Committed Q-learning,200,510,1.0
Committed Q-learning,200,511,1.0
Committed Q-learning,200,512,1.0
Committed Q-learning,200,513,1.0
Committed Q-learning,200,514,1.0
Committed Q-learning,200,515,1.0
Committed Q-learning,200,516,1.0
Committed Q-learning,200,517,1.0
Committed Q-learning,200,518,1.0
Committed Q-learning,200,519,1.0
Committed Q-learning,200,520,1.0
Committed Q-learning,200,521,1.0
Committed Q-learning,200,522,1.0
Committed Q-learning,200,523,1.0
Committed Q-learning,200,524,1.0
Committed Q-learning,200,525,1.0
Committed Q-learning,200,526,1.0
Committed Q-learning,200,527,1.0
Committed Q-learning,200,528,1.0
Committed Q-learning,200,529,1.0
Committed Q-learning,200,530,1.0
Committed Q-learning,200,531,1.0
Committed Q-learning,200,532,1.0
Committed Q-learning,200,533,1.0
Committed Q-learning,200,534,1.0
Committed Q-learning,200,535,1.0
Committed Q-learning,200,536,1.0
Committed Q-learning,200,537,1.0
Committed Q-learning,200,538,1.0
Committed Q-learning,200,539,1.0
Committed Q-learning,200,540,1.0
Committed Q-learning,200,541,1.0
Committed Q-learning,200,542,1.0
Committed Q-learning,200,543,1.0
Committed Q-learning,200,544,1.0
Committed Q-learning,200,545,1.0
Committed Q-learning,200,546,1.0
Committed Q-learning,200,547,1.0
Committed Q-learning,200,548,1.0
Committed Q-learning,200,549,1.0
Committed Q-learning,200,550,1.0
Committed Q-learning,200,551,1.0
Committed Q-learning,200,552,1.0
Committed Q-learning,200,553,1.0
Committed Q-learning,200,554,1.0
Committed Q-learning,200,555,1.0
Committed Q-learning,200,556,1.0
Committed Q-learning,200,557,1.0
Committed Q-learning,200,558,1.0
Committed Q-learning,200,559,1.0
Committed Q-learning,200,560,1.0
Committed Q-learning,200,561,1.0
Committed Q-learning,200,562,1.0
Committed Q-learning,200,563,1.0
Committed Q-learning,200,564,1.0
Committed Q-learning,200,565,1.0
Committed Q-learning,200,566,1.0
Committed Q-learning,200,567,1.0
Committed Q-learning,200,568,1.0
Committed Q-learning,200,569,1.0
Committed Q-learning,200,570,1.0
Committed Q-learning,200,571,1.0
Committed Q-learning,200,572,1.0
Committed Q-learning,200,573,1.0
Committed Q-learning,200,574,1.0
Committed Q-learning,200,575,1.0
Committed Q-learning,200,576,1.0
Committed Q-learning,200,577,1.0
Committed Q-learning,200,578,1.0
Committed Q-learning,200,579,1.0
Committed Q-learning,200,580,1.0
Committed Q-learning,200,581,1.0
Committed Q-learning,200,582,1.0
Committed Q-learning,200,583,1.0
Committed Q-learning,200,584,1.0
Committed Q-learning,200,585,1.0
Committed Q-learning,200,586,1.0
Committed Q-learning,200,587,1.0
Committed Q-learning,200,588,1.0
Committed Q-learning,200,589,1.0
Committed Q-learning,200,590,1.0
Committed Q-learning,200,591,1.0
Committed Q-learning,200,592,1.0
Committed Q-learning,200,593,1.0
Committed Q-learning,200,594,1.0
Committed Q-learning,200,595,1.0
Committed Q-learning,200,596,1.0
Committed Q-learning,200,597,1.0
Committed Q-learning,200,598,1.0
Committed Q-learning,200,599,1.0
Committed Q-learning,200,600,1.0
Committed Q-learning,200,601,1.0
Committed Q-learning,200,602,1.0
Committed Q-learning,200,603,1.0
Committed Q-learning,200,604,1.0
Committed Q-learning,200,605,1.0
Committed Q-learning,200,606,1.0
Committed Q-learning,200,607,1.0
Committed Q-learning,200,608,1.0
Committed Q-learning,200,609,1.0
Committed Q-learning,200,610,1.0
Committed Q-learning,200,611,1.0
Committed Q-learning,200,612,1.0
Committed Q-learning,200,613,1.0
Committed Q-learning,200,614,1.0
Committed Q-learning,200,615,1.0
Committed Q-learning,200,616,1.0
Committed Q-learning,200,617,1.0
Committed Q-learning,200,618,1.0
Committed Q-learning,200,619,1.0
Committed Q-learning,200,620,1.0
Committed Q-learning,200,621,1.0
Committed Q-learning,200,622,1.0
Committed Q-learning,200,623,1.0
Committed Q-learning,200,624,1.0
Committed Q-learning,200,625,1.0
Committed Q-learning,200,626,1.0
Committed Q-learning,200,627,1.0
Committed Q-learning,200,628,1.0
Committed Q-learning,200,629,1.0
Committed Q-learning,200,630,1.0
Committed Q-learning,200,631,1.0
Committed Q-learning,200,632,1.0
Committed Q-learning,200,633,1.0
Committed Q-learning,200,634,1.0
Committed Q-learning,200,635,1.0
Committed Q-learning,200,636,1.0
Committed Q-learning,200,637,1.0
Committed Q-learning,200,638,1.0
Committed Q-learning,200,639,1.0
Committed Q-learning,200,640,1.0
Committed Q-learning,200,641,1.0
Committed Q-learning,200,642,1.0
Committed Q-learning,200,643,1.0
Committed Q-learning,200,644,1.0
Committed Q-learning,200,645,1.0
Committed Q-learning,200,646,1.0
Committed Q-learning,200,647,1.0
Committed Q-learning,200,648,1.0
Committed Q-learning,200,649,1.0
Committed Q-learning,200,650,1.0
Committed Q-learning,200,651,1.0
Committed Q-learning,200,652,1.0
Committed Q-learning,200,653,1.0
Committed Q-learning,200,654,1.0
Committed Q-learning,200,655,1.0
Committed Q-learning,200,656,1.0
Committed Q-learning,200,657,1.0
Committed Q-learning,200,658,1.0
Committed Q-learning,200,659,1.0
Committed Q-learning,200,660,1.0
Committed Q-learning,200,661,1.0
Committed Q-learning,200,662,1.0
Committed Q-learning,200,663,1.0
Committed Q-learning,200,664,1.0
Committed Q-learning,200,665,1.0
Committed Q-learning,200,666,1.0
Committed Q-learning,200,667,1.0
Committed Q-learning,200,668,1.0
Committed Q-learning,200,669,1.0
Committed Q-learning,200,670,1.0
Committed Q-learning,200,671,1.0
Committed Q-learning,200,672,1.0
Committed Q-learning,200,673,1.0
Committed Q-learning,200,674,1.0
Committed Q-learning,200,675,1.0
Committed Q-learning,200,676,1.0
Committed Q-learning,200,677,1.0
Committed Q-learning,200,678,1.0
Committed Q-learning,200,679,1.0
Committed Q-learning,200,680,1.0
Committed Q-learning,200,681,1.0
Committed Q-learning,200,682,1.0
Committed Q-learning,200,683,1.0
Committed Q-learning,200,684,1.0
Committed Q-learning,200,685,1.0
Committed Q-learning,200,686,1.0
Committed Q-learning,200,687,1.0
Committed Q-learning,200,688,1.0
Committed Q-learning,200,689,1.0
Committed Q-learning,200,690,1.0
Committed Q-learning,200,691,1.0
Committed Q-learning,200,692,1.0
Committed Q-learning,200,693,1.0
Committed Q-learning,200,694,1.0
Committed Q-learning,200,695,1.0
Committed Q-learning,200,696,1.0
Committed Q-learning,200,697,1.0
Committed Q-learning,200,698,1.0
Committed Q-learning,200,699,1.0
Committed Q-learning,200,700,1.0
Committed Q-learning,200,701,1.0
Committed Q-learning,200,702,1.0
Committed Q-learning,200,703,1.0
Committed Q-learning,200,704,1.0
Committed Q-learning,200,705,1.0
Committed Q-learning,200,706,1.0
Committed Q-learning,200,707,1.0
Committed Q-learning,200,708,1.0
Committed Q-learning,200,709,1.0
Committed Q-learning,200,710,1.0
Committed Q-learning,200,711,1.0
Committed Q-learning,200,712,1.0
Committed Q-learning,200,713,1.0
Committed Q-learning,200,714,1.0
Committed Q-learning,200,715,1.0
Committed Q-learning,200,716,1.0
Committed Q-learning,200,717,1.0
Committed Q-learning,200,718,1.0
Committed Q-learning,200,719,1.0
Committed Q-learning,200,720,1.0
Committed Q-learning,200,721,1.0
Committed Q-learning,200,722,1.0
Committed Q-learning,200,723,1.0
Committed Q-learning,200,724,1.0
Committed Q-learning,200,725,1.0
Committed Q-learning,200,726,1.0
Committed Q-learning,200,727,1.0
Committed Q-learning,200,728,1.0
Committed Q-learning,200,729,1.0
Committed Q-learning,200,730,1.0
Committed Q-learning,200,731,1.0
Committed Q-learning,200,732,1.0
Committed Q-learning,200,733,1.0
Committed Q-learning,200,734,1.0
Committed Q-learning,200,735,1.0
Committed Q-learning,200,736,1.0
Committed Q-learning,200,737,1.0
Committed Q-learning,200,738,1.0
Committed Q-learning,200,739,1.0
Committed Q-learning,200,740,1.0
Committed Q-learning,200,741,1.0
Committed Q-learning,200,742,1.0
Committed Q-learning,200,743,1.0
Committed Q-learning,200,744,1.0
Committed Q-learning,200,745,1.0
Committed Q-learning,200,746,1.0
Committed Q-learning,200,747,1.0
Committed Q-learning,200,748,1.0
Committed Q-learning,200,749,1.0
Committed Q-learning,200,750,1.0
Committed Q-learning,200,751,1.0
Committed Q-learning,200,752,1.0
Committed Q-learning,200,753,1.0
Committed Q-learning,200,754,1.0
Committed Q-learning,200,755,1.0
Committed Q-learning,200,756,1.0
Committed Q-learning,200,757,1.0
Committed Q-learning,200,758,1.0
Committed Q-learning,200,759,1.0
Committed Q-learning,200,760,1.0
Committed Q-learning,200,761,1.0
Committed Q-learning,200,762,1.0
Committed Q-learning,200,763,1.0
Committed Q-learning,200,764,1.0
Committed Q-learning,200,765,1.0
Committed Q-learning,200,766,1.0
Committed Q-learning,200,767,1.0
Committed Q-learning,200,768,1.0
Committed Q-learning,200,769,1.0
Committed Q-learning,200,770,1.0
Committed Q-learning,200,771,1.0
Committed Q-learning,200,772,1.0
Committed Q-learning,200,773,1.0
Committed Q-learning,200,774,1.0
Committed Q-learning,200,775,1.0
Committed Q-learning,200,776,1.0
Committed Q-learning,200,777,1.0
Committed Q-learning,200,778,1.0
Committed Q-learning,200,779,1.0
Committed Q-learning,200,780,1.0
Committed Q-learning,200,781,1.0
Committed Q-learning,200,782,1.0
Committed Q-learning,200,783,1.0
Committed Q-learning,200,784,1.0
Committed Q-learning,200,785,1.0
Committed Q-learning,200,786,1.0
Committed Q-learning,200,787,1.0
Committed Q-learning,200,788,1.0
Committed Q-learning,200,789,1.0
Committed Q-learning,200,790,1.0
Committed Q-learning,200,791,1.0
Committed Q-learning,200,792,1.0
Committed Q-learning,200,793,1.0
Committed Q-learning,200,794,1.0
Committed Q-learning,200,795,1.0
Committed Q-learning,200,796,1.0
Committed Q-learning,200,797,1.0
Committed Q-learning,200,798,1.0
Committed Q-learning,200,799,1.0
Committed Q-learning,200,800,1.0
Committed Q-learning,200,801,1.0
Committed Q-learning,200,802,1.0
Committed Q-learning,200,803,1.0
Committed Q-learning,200,804,1.0
Committed Q-learning,200,805,1.0
Committed Q-learning,200,806,1.0
Committed Q-learning,200,807,1.0
Committed Q-learning,200,808,1.0
Committed Q-learning,200,809,1.0
Committed Q-learning,200,810,1.0
Committed Q-learning,200,811,1.0
Committed Q-learning,200,812,1.0
Committed Q-learning,200,813,1.0
Committed Q-learning,200,814,1.0
Committed Q-learning,200,815,1.0
Committed Q-learning,200,816,1.0
Committed Q-learning,200,817,1.0
Committed Q-learning,200,818,1.0
Committed Q-learning,200,819,1.0
Committed Q-learning,200,820,1.0
Committed Q-learning,200,821,1.0
Committed Q-learning,200,822,1.0
Committed Q-learning,200,823,1.0
Committed Q-learning,200,824,1.0
Committed Q-learning,200,825,1.0
Committed Q-learning,200,826,1.0
Committed Q-learning,200,827,1.0
Committed Q-learning,200,828,1.0
Committed Q-learning,200,829,1.0
Committed Q-learning,200,830,1.0
Committed Q-learning,200,831,1.0
Committed Q-learning,200,832,1.0
Committed Q-learning,200,833,1.0
Committed Q-learning,200,834,1.0
Committed Q-learning,200,835,1.0
Committed Q-learning,200,836,1.0
Committed Q-learning,200,837,1.0
Committed Q-learning,200,838,1.0
Committed Q-learning,200,839,1.0
Committed Q-learning,200,840,1.0
Committed Q-learning,200,841,1.0
Committed Q-learning,200,842,1.0
Committed Q-learning,200,843,1.0
Committed Q-learning,200,844,1.0
Committed Q-learning,200,845,1.0
Committed Q-learning,200,846,1.0
Committed Q-learning,200,847,1.0
Committed Q-learning,200,848,1.0
Committed Q-learning,200,849,1.0
Committed Q-learning,200,850,1.0
Committed Q-learning,200,851,1.0
Committed Q-learning,200,852,1.0
Committed Q-learning,200,853,1.0
Committed Q-learning,200,854,1.0
Committed Q-learning,200,855,1.0
Committed Q-learning,200,856,1.0
Committed Q-learning,200,857,1.0
Committed Q-learning,200,858,1.0
Committed Q-learning,200,859,1.0
Committed Q-learning,200,860,1.0
Committed Q-learning,200,861,1.0
Committed Q-learning,200,862,1.0
Committed Q-learning,200,863,1.0
Committed Q-learning,200,864,1.0
Committed Q-learning,200,865,1.0
Committed Q-learning,200,866,1.0
Committed Q-learning,200,867,1.0
Committed Q-learning,200,868,1.0
Committed Q-learning,200,869,1.0
Committed Q-learning,200,870,1.0
Committed Q-learning,200,871,1.0
Committed Q-learning,200,872,1.0
Committed Q-learning,200,873,1.0
Committed Q-learning,200,874,1.0
Committed Q-learning,200,875,1.0
Committed Q-learning,200,876,1.0
Committed Q-learning,200,877,1.0
Committed Q-learning,200,878,1.0
Committed Q-learning,200,879,1.0
Committed Q-learning,200,880,1.0
Committed Q-learning,200,881,1.0
Committed Q-learning,200,882,1.0
Committed Q-learning,200,883,1.0
Committed Q-learning,200,884,1.0
Committed Q-learning,200,885,1.0
Committed Q-learning,200,886,1.0
Committed Q-learning,200,887,1.0
Committed Q-learning,200,888,1.0
Committed Q-learning,200,889,1.0
Committed Q-learning,200,890,1.0
Committed Q-learning,200,891,1.0
Committed Q-learning,200,892,1.0
Committed Q-learning,200,893,1.0
Committed Q-learning,200,894,1.0
Committed Q-learning,200,895,1.0
Committed Q-learning,200,896,1.0
Committed Q-learning,200,897,1.0
Committed Q-learning,200,898,1.0
Committed Q-learning,200,899,1.0
Committed Q-learning,200,900,1.0
Committed Q-learning,200,901,1.0
Committed Q-learning,200,902,1.0
Committed Q-learning,200,903,1.0
Committed Q-learning,200,904,1.0
Committed Q-learning,200,905,1.0
Committed Q-learning,200,906,1.0
Committed Q-learning,200,907,1.0
Committed Q-learning,200,908,1.0
Committed Q-learning,200,909,1.0
Committed Q-learning,200,910,1.0
Committed Q-learning,200,911,1.0
Committed Q-learning,200,912,1.0
Committed Q-learning,200,913,1.0
Committed Q-learning,200,914,1.0
Committed Q-learning,200,915,1.0
Committed Q-learning,200,916,1.0
Committed Q-learning,200,917,1.0
Committed Q-learning,200,918,1.0
Committed Q-learning,200,919,1.0
Committed Q-learning,200,920,1.0
Committed Q-learning,200,921,1.0
Committed Q-learning,200,922,1.0
Committed Q-learning,200,923,1.0
Committed Q-learning,200,924,1.0
Committed Q-learning,200,925,1.0
Committed Q-learning,200,926,1.0
Committed Q-learning,200,927,1.0
Committed Q-learning,200,928,1.0
Committed Q-learning,200,929,1.0
Committed Q-learning,200,930,1.0
Committed Q-learning,200,931,1.0
Committed Q-learning,200,932,1.0
Committed Q-learning,200,933,1.0
Committed Q-learning,200,934,1.0
Committed Q-learning,200,935,1.0
Committed Q-learning,200,936,1.0
Committed Q-learning,200,937,1.0
Committed Q-learning,200,938,1.0
Committed Q-learning,200,939,1.0
Committed Q-learning,200,940,1.0
Committed Q-learning,200,941,1.0
Committed Q-learning,200,942,1.0
Committed Q-learning,200,943,1.0
Committed Q-learning,200,944,1.0
Committed Q-learning,200,945,1.0
Committed Q-learning,200,946,1.0
Committed Q-learning,200,947,1.0
Committed Q-learning,200,948,1.0
Committed Q-learning,200,949,1.0
Committed Q-learning,200,950,1.0
Committed Q-learning,200,951,1.0
Committed Q-learning,200,952,1.0
Committed Q-learning,200,953,1.0
Committed Q-learning,200,954,1.0
Committed Q-learning,200,955,1.0
Committed Q-learning,200,956,1.0
Committed Q-learning,200,957,1.0
Committed Q-learning,200,958,1.0
Committed Q-learning,200,959,1.0
Committed Q-learning,200,960,1.0
Committed Q-learning,200,961,1.0
Committed Q-learning,200,962,1.0
Committed Q-learning,200,963,1.0
Committed Q-learning,200,964,1.0
Committed Q-learning,200,965,1.0
Committed Q-learning,200,966,1.0
Committed Q-learning,200,967,1.0
Committed Q-learning,200,968,1.0
Committed Q-learning,200,969,1.0
Committed Q-learning,200,970,1.0
Committed Q-learning,200,971,1.0
Committed Q-learning,200,972,1.0
Committed Q-learning,200,973,1.0
Committed Q-learning,200,974,1.0
Committed Q-learning,200,975,1.0
Committed Q-learning,200,976,1.0
Committed Q-learning,200,977,1.0
Committed Q-learning,200,978,1.0
Committed Q-learning,200,979,1.0
Committed Q-learning,200,980,1.0
Committed Q-learning,200,981,1.0
Committed Q-learning,200,982,1.0
Committed Q-learning,200,983,1.0
Committed Q-learning,200,984,1.0
Committed Q-learning,200,985,1.0
Committed Q-learning,200,986,1.0
Committed Q-learning,200,987,1.0
Committed Q-learning,200,988,1.0
Committed Q-learning,200,989,1.0
Committed Q-learning,200,990,1.0
Committed Q-learning,200,991,1.0
Committed Q-learning,200,992,1.0
Committed Q-learning,200,993,1.0
Committed Q-learning,200,994,1.0
Committed Q-learning,200,995,1.0
Committed Q-learning,200,996,1.0
Committed Q-learning,200,997,1.0
Committed Q-learning,200,998,1.0
Committed Q-learning,200,999,1.0
Committed Q-learning,200,1000,1.0
Regular Q-learning,5,1,0.2409999966621399
Regular Q-learning,5,2,0.2029999941587448
Regular Q-learning,5,3,0.14100000262260437
Regular Q-learning,5,4,0.13699999451637268
Regular Q-learning,5,5,0.11599999666213989
Regular Q-learning,5,6,0.10999999940395355
Regular Q-learning,5,7,0.10400000214576721
Regular Q-learning,5,8,0.12800000607967377
Regular Q-learning,5,9,0.11500000208616257
Regular Q-learning,5,10,0.12099999934434891
Regular Q-learning,5,11,0.125
Regular Q-learning,5,12,0.14100000262260437
Regular Q-learning,5,13,0.12800000607967377
Regular Q-learning,5,14,0.1420000046491623
Regular Q-learning,5,15,0.12800000607967377
Regular Q-learning,5,16,0.13300000131130219
Regular Q-learning,5,17,0.12999999523162842
Regular Q-learning,5,18,0.13600000739097595
Regular Q-learning,5,19,0.1289999932050705
Regular Q-learning,5,20,0.13199999928474426
Regular Q-learning,5,21,0.12800000607967377
Regular Q-learning,5,22,0.125
Regular Q-learning,5,23,0.11999999731779099
Regular Q-learning,5,24,0.12600000202655792
Regular Q-learning,5,25,0.12099999934434891
Regular Q-learning,5,26,0.12300000339746475
Regular Q-learning,5,27,0.11299999803304672
Regular Q-learning,5,28,0.11400000005960464
Regular Q-learning,5,29,0.10599999874830246
Regular Q-learning,5,30,0.0989999994635582
Regular Q-learning,5,31,0.11100000143051147
Regular Q-learning,5,32,0.10300000011920929
Regular Q-learning,5,33,0.09600000083446503
Regular Q-learning,5,34,0.10700000077486038
Regular Q-learning,5,35,0.09300000220537186
Regular Q-learning,5,36,0.09700000286102295
Regular Q-learning,5,37,0.08799999952316284
Regular Q-learning,5,38,0.08799999952316284
Regular Q-learning,5,39,0.09099999815225601
Regular Q-learning,5,40,0.08299999684095383
Regular Q-learning,5,41,0.09099999815225601
Regular Q-learning,5,42,0.08299999684095383
Regular Q-learning,5,43,0.08399999886751175
Regular Q-learning,5,44,0.07500000298023224
Regular Q-learning,5,45,0.08699999749660492
Regular Q-learning,5,46,0.07599999755620956
Regular Q-learning,5,47,0.09099999815225601
Regular Q-learning,5,48,0.07100000232458115
Regular Q-learning,5,49,0.07500000298023224
Regular Q-learning,5,50,0.07500000298023224
Regular Q-learning,5,51,0.07699999958276749
Regular Q-learning,5,52,0.07500000298023224
Regular Q-learning,5,53,0.07400000095367432
Regular Q-learning,5,54,0.07100000232458115
Regular Q-learning,5,55,0.0820000022649765
Regular Q-learning,5,56,0.07699999958276749
Regular Q-learning,5,57,0.07900000363588333
Regular Q-learning,5,58,0.07100000232458115
Regular Q-learning,5,59,0.08100000023841858
Regular Q-learning,5,60,0.07999999821186066
Regular Q-learning,5,61,0.07900000363588333
Regular Q-learning,5,62,0.07100000232458115
Regular Q-learning,5,63,0.0729999989271164
Regular Q-learning,5,64,0.07500000298023224
Regular Q-learning,5,65,0.07199999690055847
Regular Q-learning,5,66,0.06800000369548798
Regular Q-learning,5,67,0.06599999964237213
Regular Q-learning,5,68,0.07199999690055847
Regular Q-learning,5,69,0.06800000369548798
Regular Q-learning,5,70,0.06199999898672104
Regular Q-learning,5,71,0.06700000166893005
Regular Q-learning,5,72,0.07100000232458115
Regular Q-learning,5,73,0.0729999989271164
Regular Q-learning,5,74,0.0689999982714653
Regular Q-learning,5,75,0.06700000166893005
Regular Q-learning,5,76,0.07199999690055847
Regular Q-learning,5,77,0.07599999755620956
Regular Q-learning,5,78,0.06700000166893005
Regular Q-learning,5,79,0.06800000369548798
Regular Q-learning,5,80,0.06599999964237213
Regular Q-learning,5,81,0.07100000232458115
Regular Q-learning,5,82,0.06800000369548798
Regular Q-learning,5,83,0.06499999761581421
Regular Q-learning,5,84,0.07199999690055847
Regular Q-learning,5,85,0.06499999761581421
Regular Q-learning,5,86,0.06300000101327896
Regular Q-learning,5,87,0.0560000017285347
Regular Q-learning,5,88,0.06499999761581421
Regular Q-learning,5,89,0.06700000166893005
Regular Q-learning,5,90,0.06199999898672104
Regular Q-learning,5,91,0.06400000303983688
Regular Q-learning,5,92,0.06499999761581421
Regular Q-learning,5,93,0.06599999964237213
Regular Q-learning,5,94,0.06700000166893005
Regular Q-learning,5,95,0.06599999964237213
Regular Q-learning,5,96,0.06300000101327896
Regular Q-learning,5,97,0.06599999964237213
Regular Q-learning,5,98,0.06700000166893005
Regular Q-learning,5,99,0.06599999964237213
Regular Q-learning,5,100,0.06800000369548798
Regular Q-learning,5,101,0.06599999964237213
Regular Q-learning,5,102,0.06400000303983688
Regular Q-learning,5,103,0.06300000101327896
Regular Q-learning,5,104,0.06499999761581421
Regular Q-learning,5,105,0.06300000101327896
Regular Q-learning,5,106,0.06400000303983688
Regular Q-learning,5,107,0.06599999964237213
Regular Q-learning,5,108,0.06599999964237213
Regular Q-learning,5,109,0.06400000303983688
Regular Q-learning,5,110,0.06199999898672104
Regular Q-learning,5,111,0.06499999761581421
Regular Q-learning,5,112,0.06499999761581421
Regular Q-learning,5,113,0.06599999964237213
Regular Q-learning,5,114,0.06599999964237213
Regular Q-learning,5,115,0.05999999865889549
Regular Q-learning,5,116,0.06599999964237213
Regular Q-learning,5,117,0.06800000369548798
Regular Q-learning,5,118,0.06300000101327896
Regular Q-learning,5,119,0.0689999982714653
Regular Q-learning,5,120,0.061000000685453415
Regular Q-learning,5,121,0.06599999964237213
Regular Q-learning,5,122,0.06199999898672104
Regular Q-learning,5,123,0.06800000369548798
Regular Q-learning,5,124,0.06300000101327896
Regular Q-learning,5,125,0.0689999982714653
Regular Q-learning,5,126,0.06199999898672104
Regular Q-learning,5,127,0.06400000303983688
Regular Q-learning,5,128,0.05999999865889549
Regular Q-learning,5,129,0.06300000101327896
Regular Q-learning,5,130,0.0560000017285347
Regular Q-learning,5,131,0.06499999761581421
Regular Q-learning,5,132,0.05900000035762787
Regular Q-learning,5,133,0.06499999761581421
Regular Q-learning,5,134,0.05900000035762787
Regular Q-learning,5,135,0.06199999898672104
Regular Q-learning,5,136,0.05900000035762787
Regular Q-learning,5,137,0.06800000369548798
Regular Q-learning,5,138,0.050999999046325684
Regular Q-learning,5,139,0.06400000303983688
Regular Q-learning,5,140,0.05700000002980232
Regular Q-learning,5,141,0.06499999761581421
Regular Q-learning,5,142,0.05400000140070915
Regular Q-learning,5,143,0.057999998331069946
Regular Q-learning,5,144,0.054999999701976776
Regular Q-learning,5,145,0.07000000029802322
Regular Q-learning,5,146,0.05700000002980232
Regular Q-learning,5,147,0.06700000166893005
Regular Q-learning,5,148,0.061000000685453415
Regular Q-learning,5,149,0.0689999982714653
Regular Q-learning,5,150,0.0560000017285347
Regular Q-learning,5,151,0.06700000166893005
Regular Q-learning,5,152,0.06199999898672104
Regular Q-learning,5,153,0.06300000101327896
Regular Q-learning,5,154,0.05999999865889549
Regular Q-learning,5,155,0.06800000369548798
Regular Q-learning,5,156,0.06599999964237213
Regular Q-learning,5,157,0.06599999964237213
Regular Q-learning,5,158,0.05999999865889549
Regular Q-learning,5,159,0.06700000166893005
Regular Q-learning,5,160,0.06400000303983688
Regular Q-learning,5,161,0.06599999964237213
Regular Q-learning,5,162,0.05999999865889549
Regular Q-learning,5,163,0.06700000166893005
Regular Q-learning,5,164,0.05900000035762787
Regular Q-learning,5,165,0.06199999898672104
Regular Q-learning,5,166,0.05700000002980232
Regular Q-learning,5,167,0.06700000166893005
Regular Q-learning,5,168,0.05900000035762787
Regular Q-learning,5,169,0.06700000166893005
Regular Q-learning,5,170,0.05000000074505806
Regular Q-learning,5,171,0.06700000166893005
Regular Q-learning,5,172,0.05900000035762787
Regular Q-learning,5,173,0.06499999761581421
Regular Q-learning,5,174,0.061000000685453415
Regular Q-learning,5,175,0.0689999982714653
Regular Q-learning,5,176,0.05900000035762787
Regular Q-learning,5,177,0.06400000303983688
Regular Q-learning,5,178,0.0560000017285347
Regular Q-learning,5,179,0.06300000101327896
Regular Q-learning,5,180,0.05900000035762787
Regular Q-learning,5,181,0.06499999761581421
Regular Q-learning,5,182,0.057999998331069946
Regular Q-learning,5,183,0.06300000101327896
Regular Q-learning,5,184,0.05999999865889549
Regular Q-learning,5,185,0.06599999964237213
Regular Q-learning,5,186,0.05700000002980232
Regular Q-learning,5,187,0.06300000101327896
Regular Q-learning,5,188,0.061000000685453415
Regular Q-learning,5,189,0.06700000166893005
Regular Q-learning,5,190,0.0560000017285347
Regular Q-learning,5,191,0.06499999761581421
Regular Q-learning,5,192,0.06400000303983688
Regular Q-learning,5,193,0.06599999964237213
Regular Q-learning,5,194,0.05700000002980232
Regular Q-learning,5,195,0.06400000303983688
Regular Q-learning,5,196,0.061000000685453415
Regular Q-learning,5,197,0.06199999898672104
Regular Q-learning,5,198,0.05400000140070915
Regular Q-learning,5,199,0.061000000685453415
Regular Q-learning,5,200,0.06499999761581421
Regular Q-learning,5,201,0.06400000303983688
Regular Q-learning,5,202,0.05400000140070915
Regular Q-learning,5,203,0.061000000685453415
Regular Q-learning,5,204,0.06199999898672104
Regular Q-learning,5,205,0.06199999898672104
Regular Q-learning,5,206,0.054999999701976776
Regular Q-learning,5,207,0.06300000101327896
Regular Q-learning,5,208,0.05700000002980232
Regular Q-learning,5,209,0.06300000101327896
Regular Q-learning,5,210,0.05400000140070915
Regular Q-learning,5,211,0.06599999964237213
Regular Q-learning,5,212,0.057999998331069946
Regular Q-learning,5,213,0.06300000101327896
Regular Q-learning,5,214,0.052000001072883606
Regular Q-learning,5,215,0.06300000101327896
Regular Q-learning,5,216,0.05700000002980232
Regular Q-learning,5,217,0.06499999761581421
Regular Q-learning,5,218,0.05400000140070915
Regular Q-learning,5,219,0.061000000685453415
Regular Q-learning,5,220,0.06499999761581421
Regular Q-learning,5,221,0.0560000017285347
Regular Q-learning,5,222,0.054999999701976776
Regular Q-learning,5,223,0.061000000685453415
Regular Q-learning,5,224,0.05900000035762787
Regular Q-learning,5,225,0.05900000035762787
Regular Q-learning,5,226,0.05400000140070915
Regular Q-learning,5,227,0.06300000101327896
Regular Q-learning,5,228,0.057999998331069946
Regular Q-learning,5,229,0.06400000303983688
Regular Q-learning,5,230,0.05400000140070915
Regular Q-learning,5,231,0.061000000685453415
Regular Q-learning,5,232,0.057999998331069946
Regular Q-learning,5,233,0.05900000035762787
Regular Q-learning,5,234,0.052000001072883606
Regular Q-learning,5,235,0.06300000101327896
Regular Q-learning,5,236,0.057999998331069946
Regular Q-learning,5,237,0.06300000101327896
Regular Q-learning,5,238,0.0560000017285347
Regular Q-learning,5,239,0.06700000166893005
Regular Q-learning,5,240,0.0560000017285347
Regular Q-learning,5,241,0.05999999865889549
Regular Q-learning,5,242,0.05000000074505806
Regular Q-learning,5,243,0.06400000303983688
Regular Q-learning,5,244,0.061000000685453415
Regular Q-learning,5,245,0.05999999865889549
Regular Q-learning,5,246,0.0560000017285347
Regular Q-learning,5,247,0.05999999865889549
Regular Q-learning,5,248,0.05900000035762787
Regular Q-learning,5,249,0.061000000685453415
Regular Q-learning,5,250,0.05700000002980232
Regular Q-learning,5,251,0.061000000685453415
Regular Q-learning,5,252,0.05900000035762787
Regular Q-learning,5,253,0.061000000685453415
Regular Q-learning,5,254,0.054999999701976776
Regular Q-learning,5,255,0.06400000303983688
Regular Q-learning,5,256,0.05700000002980232
Regular Q-learning,5,257,0.05999999865889549
Regular Q-learning,5,258,0.057999998331069946
Regular Q-learning,5,259,0.057999998331069946
Regular Q-learning,5,260,0.05999999865889549
Regular Q-learning,5,261,0.06199999898672104
Regular Q-learning,5,262,0.0560000017285347
Regular Q-learning,5,263,0.06300000101327896
Regular Q-learning,5,264,0.05900000035762787
Regular Q-learning,5,265,0.06199999898672104
Regular Q-learning,5,266,0.05700000002980232
Regular Q-learning,5,267,0.06300000101327896
Regular Q-learning,5,268,0.057999998331069946
Regular Q-learning,5,269,0.05900000035762787
Regular Q-learning,5,270,0.054999999701976776
Regular Q-learning,5,271,0.06199999898672104
Regular Q-learning,5,272,0.057999998331069946
Regular Q-learning,5,273,0.05999999865889549
Regular Q-learning,5,274,0.05400000140070915
Regular Q-learning,5,275,0.06199999898672104
Regular Q-learning,5,276,0.05999999865889549
Regular Q-learning,5,277,0.05700000002980232
Regular Q-learning,5,278,0.054999999701976776
Regular Q-learning,5,279,0.06199999898672104
Regular Q-learning,5,280,0.06199999898672104
Regular Q-learning,5,281,0.05999999865889549
Regular Q-learning,5,282,0.054999999701976776
Regular Q-learning,5,283,0.05900000035762787
Regular Q-learning,5,284,0.05900000035762787
Regular Q-learning,5,285,0.05999999865889549
Regular Q-learning,5,286,0.054999999701976776
Regular Q-learning,5,287,0.06300000101327896
Regular Q-learning,5,288,0.05999999865889549
Regular Q-learning,5,289,0.05900000035762787
Regular Q-learning,5,290,0.05700000002980232
Regular Q-learning,5,291,0.05700000002980232
Regular Q-learning,5,292,0.05999999865889549
Regular Q-learning,5,293,0.05999999865889549
Regular Q-learning,5,294,0.0560000017285347
Regular Q-learning,5,295,0.05999999865889549
Regular Q-learning,5,296,0.05700000002980232
Regular Q-learning,5,297,0.05900000035762787
Regular Q-learning,5,298,0.054999999701976776
Regular Q-learning,5,299,0.05400000140070915
Regular Q-learning,5,300,0.061000000685453415
Regular Q-learning,5,301,0.05900000035762787
Regular Q-learning,5,302,0.054999999701976776
Regular Q-learning,5,303,0.0560000017285347
Regular Q-learning,5,304,0.05700000002980232
Regular Q-learning,5,305,0.057999998331069946
Regular Q-learning,5,306,0.05400000140070915
Regular Q-learning,5,307,0.054999999701976776
Regular Q-learning,5,308,0.057999998331069946
Regular Q-learning,5,309,0.05900000035762787
Regular Q-learning,5,310,0.052000001072883606
Regular Q-learning,5,311,0.05700000002980232
Regular Q-learning,5,312,0.0560000017285347
Regular Q-learning,5,313,0.05700000002980232
Regular Q-learning,5,314,0.05299999937415123
Regular Q-learning,5,315,0.05900000035762787
Regular Q-learning,5,316,0.0560000017285347
Regular Q-learning,5,317,0.05999999865889549
Regular Q-learning,5,318,0.05400000140070915
Regular Q-learning,5,319,0.057999998331069946
Regular Q-learning,5,320,0.054999999701976776
Regular Q-learning,5,321,0.05999999865889549
Regular Q-learning,5,322,0.052000001072883606
Regular Q-learning,5,323,0.05900000035762787
Regular Q-learning,5,324,0.0560000017285347
Regular Q-learning,5,325,0.0560000017285347
Regular Q-learning,5,326,0.0560000017285347
Regular Q-learning,5,327,0.057999998331069946
Regular Q-learning,5,328,0.057999998331069946
Regular Q-learning,5,329,0.05999999865889549
Regular Q-learning,5,330,0.05900000035762787
Regular Q-learning,5,331,0.05400000140070915
Regular Q-learning,5,332,0.05700000002980232
Regular Q-learning,5,333,0.05900000035762787
Regular Q-learning,5,334,0.054999999701976776
Regular Q-learning,5,335,0.05700000002980232
Regular Q-learning,5,336,0.05700000002980232
Regular Q-learning,5,337,0.05700000002980232
Regular Q-learning,5,338,0.0560000017285347
Regular Q-learning,5,339,0.0560000017285347
Regular Q-learning,5,340,0.05999999865889549
Regular Q-learning,5,341,0.05700000002980232
Regular Q-learning,5,342,0.054999999701976776
Regular Q-learning,5,343,0.05400000140070915
Regular Q-learning,5,344,0.05900000035762787
Regular Q-learning,5,345,0.0560000017285347
Regular Q-learning,5,346,0.0560000017285347
Regular Q-learning,5,347,0.05900000035762787
Regular Q-learning,5,348,0.0560000017285347
Regular Q-learning,5,349,0.05700000002980232
Regular Q-learning,5,350,0.054999999701976776
Regular Q-learning,5,351,0.0560000017285347
Regular Q-learning,5,352,0.05999999865889549
Regular Q-learning,5,353,0.05700000002980232
Regular Q-learning,5,354,0.05400000140070915
Regular Q-learning,5,355,0.057999998331069946
Regular Q-learning,5,356,0.061000000685453415
Regular Q-learning,5,357,0.05400000140070915
Regular Q-learning,5,358,0.0560000017285347
Regular Q-learning,5,359,0.0560000017285347
Regular Q-learning,5,360,0.05999999865889549
Regular Q-learning,5,361,0.05400000140070915
Regular Q-learning,5,362,0.0560000017285347
Regular Q-learning,5,363,0.0560000017285347
Regular Q-learning,5,364,0.061000000685453415
Regular Q-learning,5,365,0.0560000017285347
Regular Q-learning,5,366,0.0560000017285347
Regular Q-learning,5,367,0.057999998331069946
Regular Q-learning,5,368,0.05999999865889549
Regular Q-learning,5,369,0.0560000017285347
Regular Q-learning,5,370,0.05299999937415123
Regular Q-learning,5,371,0.0560000017285347
Regular Q-learning,5,372,0.05900000035762787
Regular Q-learning,5,373,0.0560000017285347
Regular Q-learning,5,374,0.052000001072883606
Regular Q-learning,5,375,0.0560000017285347
Regular Q-learning,5,376,0.05700000002980232
Regular Q-learning,5,377,0.057999998331069946
Regular Q-learning,5,378,0.05299999937415123
Regular Q-learning,5,379,0.05700000002980232
Regular Q-learning,5,380,0.05700000002980232
Regular Q-learning,5,381,0.0560000017285347
Regular Q-learning,5,382,0.05400000140070915
Regular Q-learning,5,383,0.05700000002980232
Regular Q-learning,5,384,0.057999998331069946
Regular Q-learning,5,385,0.05400000140070915
Regular Q-learning,5,386,0.052000001072883606
Regular Q-learning,5,387,0.0560000017285347
Regular Q-learning,5,388,0.057999998331069946
Regular Q-learning,5,389,0.0560000017285347
Regular Q-learning,5,390,0.052000001072883606
Regular Q-learning,5,391,0.05700000002980232
Regular Q-learning,5,392,0.0560000017285347
Regular Q-learning,5,393,0.057999998331069946
Regular Q-learning,5,394,0.050999999046325684
Regular Q-learning,5,395,0.05400000140070915
Regular Q-learning,5,396,0.05900000035762787
Regular Q-learning,5,397,0.054999999701976776
Regular Q-learning,5,398,0.052000001072883606
Regular Q-learning,5,399,0.0560000017285347
Regular Q-learning,5,400,0.0560000017285347
Regular Q-learning,5,401,0.052000001072883606
Regular Q-learning,5,402,0.05400000140070915
Regular Q-learning,5,403,0.057999998331069946
Regular Q-learning,5,404,0.054999999701976776
Regular Q-learning,5,405,0.054999999701976776
Regular Q-learning,5,406,0.05400000140070915
Regular Q-learning,5,407,0.054999999701976776
Regular Q-learning,5,408,0.05400000140070915
Regular Q-learning,5,409,0.05700000002980232
Regular Q-learning,5,410,0.05299999937415123
Regular Q-learning,5,411,0.057999998331069946
Regular Q-learning,5,412,0.05400000140070915
Regular Q-learning,5,413,0.054999999701976776
Regular Q-learning,5,414,0.052000001072883606
Regular Q-learning,5,415,0.0560000017285347
Regular Q-learning,5,416,0.052000001072883606
Regular Q-learning,5,417,0.054999999701976776
Regular Q-learning,5,418,0.04899999871850014
Regular Q-learning,5,419,0.05700000002980232
Regular Q-learning,5,420,0.05400000140070915
Regular Q-learning,5,421,0.054999999701976776
Regular Q-learning,5,422,0.052000001072883606
Regular Q-learning,5,423,0.05999999865889549
Regular Q-learning,5,424,0.05299999937415123
Regular Q-learning,5,425,0.05400000140070915
Regular Q-learning,5,426,0.05000000074505806
Regular Q-learning,5,427,0.05999999865889549
Regular Q-learning,5,428,0.05400000140070915
Regular Q-learning,5,429,0.05299999937415123
Regular Q-learning,5,430,0.050999999046325684
Regular Q-learning,5,431,0.06199999898672104
Regular Q-learning,5,432,0.054999999701976776
Regular Q-learning,5,433,0.05400000140070915
Regular Q-learning,5,434,0.05299999937415123
Regular Q-learning,5,435,0.0560000017285347
Regular Q-learning,5,436,0.052000001072883606
Regular Q-learning,5,437,0.0560000017285347
Regular Q-learning,5,438,0.050999999046325684
Regular Q-learning,5,439,0.05700000002980232
Regular Q-learning,5,440,0.05299999937415123
Regular Q-learning,5,441,0.05400000140070915
Regular Q-learning,5,442,0.05400000140070915
Regular Q-learning,5,443,0.0560000017285347
Regular Q-learning,5,444,0.05400000140070915
Regular Q-learning,5,445,0.05299999937415123
Regular Q-learning,5,446,0.052000001072883606
Regular Q-learning,5,447,0.05700000002980232
Regular Q-learning,5,448,0.050999999046325684
Regular Q-learning,5,449,0.054999999701976776
Regular Q-learning,5,450,0.050999999046325684
Regular Q-learning,5,451,0.057999998331069946
Regular Q-learning,5,452,0.05299999937415123
Regular Q-learning,5,453,0.0560000017285347
Regular Q-learning,5,454,0.05299999937415123
Regular Q-learning,5,455,0.05700000002980232
Regular Q-learning,5,456,0.050999999046325684
Regular Q-learning,5,457,0.0560000017285347
Regular Q-learning,5,458,0.050999999046325684
Regular Q-learning,5,459,0.057999998331069946
Regular Q-learning,5,460,0.05000000074505806
Regular Q-learning,5,461,0.0560000017285347
Regular Q-learning,5,462,0.050999999046325684
Regular Q-learning,5,463,0.05700000002980232
Regular Q-learning,5,464,0.052000001072883606
Regular Q-learning,5,465,0.05400000140070915
Regular Q-learning,5,466,0.05299999937415123
Regular Q-learning,5,467,0.0560000017285347
Regular Q-learning,5,468,0.050999999046325684
Regular Q-learning,5,469,0.052000001072883606
Regular Q-learning,5,470,0.04899999871850014
Regular Q-learning,5,471,0.05900000035762787
Regular Q-learning,5,472,0.052000001072883606
Regular Q-learning,5,473,0.05400000140070915
Regular Q-learning,5,474,0.05400000140070915
Regular Q-learning,5,475,0.0560000017285347
Regular Q-learning,5,476,0.052000001072883606
Regular Q-learning,5,477,0.05400000140070915
Regular Q-learning,5,478,0.050999999046325684
Regular Q-learning,5,479,0.057999998331069946
Regular Q-learning,5,480,0.052000001072883606
Regular Q-learning,5,481,0.05400000140070915
Regular Q-learning,5,482,0.05000000074505806
Regular Q-learning,5,483,0.0560000017285347
Regular Q-learning,5,484,0.05400000140070915
Regular Q-learning,5,485,0.05000000074505806
Regular Q-learning,5,486,0.04899999871850014
Regular Q-learning,5,487,0.05900000035762787
Regular Q-learning,5,488,0.054999999701976776
Regular Q-learning,5,489,0.05299999937415123
Regular Q-learning,5,490,0.04699999839067459
Regular Q-learning,5,491,0.05900000035762787
Regular Q-learning,5,492,0.05299999937415123
Regular Q-learning,5,493,0.052000001072883606
Regular Q-learning,5,494,0.04699999839067459
Regular Q-learning,5,495,0.0560000017285347
Regular Q-learning,5,496,0.054999999701976776
Regular Q-learning,5,497,0.052000001072883606
Regular Q-learning,5,498,0.04800000041723251
Regular Q-learning,5,499,0.05999999865889549
Regular Q-learning,5,500,0.0560000017285347
Regular Q-learning,5,501,0.04899999871850014
Regular Q-learning,5,502,0.04800000041723251
Regular Q-learning,5,503,0.05900000035762787
Regular Q-learning,5,504,0.054999999701976776
Regular Q-learning,5,505,0.05000000074505806
Regular Q-learning,5,506,0.04600000008940697
Regular Q-learning,5,507,0.057999998331069946
Regular Q-learning,5,508,0.054999999701976776
Regular Q-learning,5,509,0.052000001072883606
Regular Q-learning,5,510,0.04800000041723251
Regular Q-learning,5,511,0.0560000017285347
Regular Q-learning,5,512,0.05299999937415123
Regular Q-learning,5,513,0.05000000074505806
Regular Q-learning,5,514,0.04899999871850014
Regular Q-learning,5,515,0.05700000002980232
Regular Q-learning,5,516,0.05400000140070915
Regular Q-learning,5,517,0.05299999937415123
Regular Q-learning,5,518,0.050999999046325684
Regular Q-learning,5,519,0.0560000017285347
Regular Q-learning,5,520,0.052000001072883606
Regular Q-learning,5,521,0.052000001072883606
Regular Q-learning,5,522,0.05000000074505806
Regular Q-learning,5,523,0.05700000002980232
Regular Q-learning,5,524,0.05400000140070915
Regular Q-learning,5,525,0.054999999701976776
Regular Q-learning,5,526,0.05000000074505806
Regular Q-learning,5,527,0.0560000017285347
Regular Q-learning,5,528,0.0560000017285347
Regular Q-learning,5,529,0.052000001072883606
Regular Q-learning,5,530,0.04699999839067459
Regular Q-learning,5,531,0.054999999701976776
Regular Q-learning,5,532,0.057999998331069946
Regular Q-learning,5,533,0.050999999046325684
Regular Q-learning,5,534,0.04899999871850014
Regular Q-learning,5,535,0.0560000017285347
Regular Q-learning,5,536,0.05700000002980232
Regular Q-learning,5,537,0.052000001072883606
Regular Q-learning,5,538,0.05000000074505806
Regular Q-learning,5,539,0.0560000017285347
Regular Q-learning,5,540,0.05400000140070915
Regular Q-learning,5,541,0.05299999937415123
Regular Q-learning,5,542,0.04800000041723251
Regular Q-learning,5,543,0.0560000017285347
Regular Q-learning,5,544,0.057999998331069946
Regular Q-learning,5,545,0.05000000074505806
Regular Q-learning,5,546,0.04800000041723251
Regular Q-learning,5,547,0.0560000017285347
Regular Q-learning,5,548,0.05299999937415123
Regular Q-learning,5,549,0.054999999701976776
Regular Q-learning,5,550,0.05000000074505806
Regular Q-learning,5,551,0.05299999937415123
Regular Q-learning,5,552,0.050999999046325684
Regular Q-learning,5,553,0.05299999937415123
Regular Q-learning,5,554,0.05000000074505806
Regular Q-learning,5,555,0.05700000002980232
Regular Q-learning,5,556,0.0560000017285347
Regular Q-learning,5,557,0.052000001072883606
Regular Q-learning,5,558,0.04899999871850014
Regular Q-learning,5,559,0.054999999701976776
Regular Q-learning,5,560,0.054999999701976776
Regular Q-learning,5,561,0.05400000140070915
Regular Q-learning,5,562,0.050999999046325684
Regular Q-learning,5,563,0.05400000140070915
Regular Q-learning,5,564,0.05400000140070915
Regular Q-learning,5,565,0.05400000140070915
Regular Q-learning,5,566,0.052000001072883606
Regular Q-learning,5,567,0.05400000140070915
Regular Q-learning,5,568,0.05299999937415123
Regular Q-learning,5,569,0.05299999937415123
Regular Q-learning,5,570,0.04899999871850014
Regular Q-learning,5,571,0.05299999937415123
Regular Q-learning,5,572,0.05400000140070915
Regular Q-learning,5,573,0.0560000017285347
Regular Q-learning,5,574,0.04899999871850014
Regular Q-learning,5,575,0.052000001072883606
Regular Q-learning,5,576,0.052000001072883606
Regular Q-learning,5,577,0.054999999701976776
Regular Q-learning,5,578,0.04899999871850014
Regular Q-learning,5,579,0.05700000002980232
Regular Q-learning,5,580,0.052000001072883606
Regular Q-learning,5,581,0.05299999937415123
Regular Q-learning,5,582,0.04899999871850014
Regular Q-learning,5,583,0.0560000017285347
Regular Q-learning,5,584,0.052000001072883606
Regular Q-learning,5,585,0.054999999701976776
Regular Q-learning,5,586,0.04899999871850014
Regular Q-learning,5,587,0.0560000017285347
Regular Q-learning,5,588,0.05000000074505806
Regular Q-learning,5,589,0.05400000140070915
Regular Q-learning,5,590,0.050999999046325684
Regular Q-learning,5,591,0.05299999937415123
Regular Q-learning,5,592,0.050999999046325684
Regular Q-learning,5,593,0.05299999937415123
Regular Q-learning,5,594,0.05000000074505806
Regular Q-learning,5,595,0.054999999701976776
Regular Q-learning,5,596,0.050999999046325684
Regular Q-learning,5,597,0.04899999871850014
Regular Q-learning,5,598,0.04800000041723251
Regular Q-learning,5,599,0.05700000002980232
Regular Q-learning,5,600,0.04899999871850014
Regular Q-learning,5,601,0.05400000140070915
Regular Q-learning,5,602,0.05400000140070915
Regular Q-learning,5,603,0.05299999937415123
Regular Q-learning,5,604,0.04800000041723251
Regular Q-learning,5,605,0.05400000140070915
Regular Q-learning,5,606,0.054999999701976776
Regular Q-learning,5,607,0.05000000074505806
Regular Q-learning,5,608,0.04800000041723251
Regular Q-learning,5,609,0.05299999937415123
Regular Q-learning,5,610,0.054999999701976776
Regular Q-learning,5,611,0.04899999871850014
Regular Q-learning,5,612,0.04800000041723251
Regular Q-learning,5,613,0.05400000140070915
Regular Q-learning,5,614,0.05400000140070915
Regular Q-learning,5,615,0.050999999046325684
Regular Q-learning,5,616,0.04899999871850014
Regular Q-learning,5,617,0.05299999937415123
Regular Q-learning,5,618,0.05400000140070915
Regular Q-learning,5,619,0.05299999937415123
Regular Q-learning,5,620,0.04899999871850014
Regular Q-learning,5,621,0.05400000140070915
Regular Q-learning,5,622,0.05400000140070915
Regular Q-learning,5,623,0.05000000074505806
Regular Q-learning,5,624,0.050999999046325684
Regular Q-learning,5,625,0.05299999937415123
Regular Q-learning,5,626,0.05299999937415123
Regular Q-learning,5,627,0.05299999937415123
Regular Q-learning,5,628,0.05000000074505806
Regular Q-learning,5,629,0.04899999871850014
Regular Q-learning,5,630,0.05000000074505806
Regular Q-learning,5,631,0.054999999701976776
Regular Q-learning,5,632,0.052000001072883606
Regular Q-learning,5,633,0.052000001072883606
Regular Q-learning,5,634,0.04899999871850014
Regular Q-learning,5,635,0.052000001072883606
Regular Q-learning,5,636,0.050999999046325684
Regular Q-learning,5,637,0.052000001072883606
Regular Q-learning,5,638,0.050999999046325684
Regular Q-learning,5,639,0.05299999937415123
Regular Q-learning,5,640,0.05000000074505806
Regular Q-learning,5,641,0.050999999046325684
Regular Q-learning,5,642,0.05000000074505806
Regular Q-learning,5,643,0.05299999937415123
Regular Q-learning,5,644,0.052000001072883606
Regular Q-learning,5,645,0.052000001072883606
Regular Q-learning,5,646,0.050999999046325684
Regular Q-learning,5,647,0.05400000140070915
Regular Q-learning,5,648,0.050999999046325684
Regular Q-learning,5,649,0.050999999046325684
Regular Q-learning,5,650,0.05000000074505806
Regular Q-learning,5,651,0.05400000140070915
Regular Q-learning,5,652,0.05000000074505806
Regular Q-learning,5,653,0.05400000140070915
Regular Q-learning,5,654,0.052000001072883606
Regular Q-learning,5,655,0.05400000140070915
Regular Q-learning,5,656,0.052000001072883606
Regular Q-learning,5,657,0.050999999046325684
Regular Q-learning,5,658,0.050999999046325684
Regular Q-learning,5,659,0.0560000017285347
Regular Q-learning,5,660,0.04899999871850014
Regular Q-learning,5,661,0.054999999701976776
Regular Q-learning,5,662,0.052000001072883606
Regular Q-learning,5,663,0.05299999937415123
Regular Q-learning,5,664,0.04800000041723251
Regular Q-learning,5,665,0.052000001072883606
Regular Q-learning,5,666,0.05000000074505806
Regular Q-learning,5,667,0.05400000140070915
Regular Q-learning,5,668,0.04899999871850014
Regular Q-learning,5,669,0.050999999046325684
Regular Q-learning,5,670,0.04899999871850014
Regular Q-learning,5,671,0.05400000140070915
Regular Q-learning,5,672,0.04699999839067459
Regular Q-learning,5,673,0.050999999046325684
Regular Q-learning,5,674,0.04899999871850014
Regular Q-learning,5,675,0.05400000140070915
Regular Q-learning,5,676,0.04899999871850014
Regular Q-learning,5,677,0.050999999046325684
Regular Q-learning,5,678,0.05000000074505806
Regular Q-learning,5,679,0.05299999937415123
Regular Q-learning,5,680,0.05000000074505806
Regular Q-learning,5,681,0.050999999046325684
Regular Q-learning,5,682,0.050999999046325684
Regular Q-learning,5,683,0.052000001072883606
Regular Q-learning,5,684,0.04800000041723251
Regular Q-learning,5,685,0.04899999871850014
Regular Q-learning,5,686,0.052000001072883606
Regular Q-learning,5,687,0.05299999937415123
Regular Q-learning,5,688,0.04800000041723251
Regular Q-learning,5,689,0.050999999046325684
Regular Q-learning,5,690,0.05000000074505806
Regular Q-learning,5,691,0.054999999701976776
Regular Q-learning,5,692,0.04899999871850014
Regular Q-learning,5,693,0.052000001072883606
Regular Q-learning,5,694,0.05000000074505806
Regular Q-learning,5,695,0.05400000140070915
Regular Q-learning,5,696,0.04699999839067459
Regular Q-learning,5,697,0.05000000074505806
Regular Q-learning,5,698,0.05000000074505806
Regular Q-learning,5,699,0.05400000140070915
Regular Q-learning,5,700,0.04699999839067459
Regular Q-learning,5,701,0.05000000074505806
Regular Q-learning,5,702,0.04899999871850014
Regular Q-learning,5,703,0.05400000140070915
Regular Q-learning,5,704,0.04800000041723251
Regular Q-learning,5,705,0.050999999046325684
Regular Q-learning,5,706,0.04800000041723251
Regular Q-learning,5,707,0.054999999701976776
Regular Q-learning,5,708,0.05000000074505806
Regular Q-learning,5,709,0.052000001072883606
Regular Q-learning,5,710,0.04800000041723251
Regular Q-learning,5,711,0.05400000140070915
Regular Q-learning,5,712,0.04899999871850014
Regular Q-learning,5,713,0.050999999046325684
Regular Q-learning,5,714,0.04699999839067459
Regular Q-learning,5,715,0.05400000140070915
Regular Q-learning,5,716,0.04699999839067459
Regular Q-learning,5,717,0.052000001072883606
Regular Q-learning,5,718,0.04800000041723251
Regular Q-learning,5,719,0.0560000017285347
Regular Q-learning,5,720,0.04699999839067459
Regular Q-learning,5,721,0.05000000074505806
Regular Q-learning,5,722,0.04800000041723251
Regular Q-learning,5,723,0.0560000017285347
Regular Q-learning,5,724,0.04800000041723251
Regular Q-learning,5,725,0.050999999046325684
Regular Q-learning,5,726,0.04899999871850014
Regular Q-learning,5,727,0.05299999937415123
Regular Q-learning,5,728,0.05000000074505806
Regular Q-learning,5,729,0.04699999839067459
Regular Q-learning,5,730,0.04899999871850014
Regular Q-learning,5,731,0.052000001072883606
Regular Q-learning,5,732,0.04899999871850014
Regular Q-learning,5,733,0.05000000074505806
Regular Q-learning,5,734,0.04899999871850014
Regular Q-learning,5,735,0.05299999937415123
Regular Q-learning,5,736,0.05000000074505806
Regular Q-learning,5,737,0.05000000074505806
Regular Q-learning,5,738,0.05000000074505806
Regular Q-learning,5,739,0.054999999701976776
Regular Q-learning,5,740,0.04699999839067459
Regular Q-learning,5,741,0.05000000074505806
Regular Q-learning,5,742,0.04800000041723251
Regular Q-learning,5,743,0.05400000140070915
Regular Q-learning,5,744,0.04600000008940697
Regular Q-learning,5,745,0.05299999937415123
Regular Q-learning,5,746,0.05000000074505806
Regular Q-learning,5,747,0.05299999937415123
Regular Q-learning,5,748,0.04600000008940697
Regular Q-learning,5,749,0.05299999937415123
Regular Q-learning,5,750,0.05000000074505806
Regular Q-learning,5,751,0.05400000140070915
Regular Q-learning,5,752,0.04699999839067459
Regular Q-learning,5,753,0.05299999937415123
Regular Q-learning,5,754,0.050999999046325684
Regular Q-learning,5,755,0.04899999871850014
Regular Q-learning,5,756,0.04800000041723251
Regular Q-learning,5,757,0.05400000140070915
Regular Q-learning,5,758,0.05000000074505806
Regular Q-learning,5,759,0.04699999839067459
Regular Q-learning,5,760,0.05000000074505806
Regular Q-learning,5,761,0.05400000140070915
Regular Q-learning,5,762,0.04899999871850014
Regular Q-learning,5,763,0.05000000074505806
Regular Q-learning,5,764,0.05000000074505806
Regular Q-learning,5,765,0.0560000017285347
Regular Q-learning,5,766,0.050999999046325684
Regular Q-learning,5,767,0.04899999871850014
Regular Q-learning,5,768,0.04800000041723251
Regular Q-learning,5,769,0.0560000017285347
Regular Q-learning,5,770,0.04699999839067459
Regular Q-learning,5,771,0.04800000041723251
Regular Q-learning,5,772,0.05000000074505806
Regular Q-learning,5,773,0.05700000002980232
Regular Q-learning,5,774,0.04800000041723251
Regular Q-learning,5,775,0.04600000008940697
Regular Q-learning,5,776,0.04800000041723251
Regular Q-learning,5,777,0.057999998331069946
Regular Q-learning,5,778,0.04800000041723251
Regular Q-learning,5,779,0.04800000041723251
Regular Q-learning,5,780,0.050999999046325684
Regular Q-learning,5,781,0.05700000002980232
Regular Q-learning,5,782,0.04899999871850014
Regular Q-learning,5,783,0.04800000041723251
Regular Q-learning,5,784,0.050999999046325684
Regular Q-learning,5,785,0.0560000017285347
Regular Q-learning,5,786,0.04800000041723251
Regular Q-learning,5,787,0.04699999839067459
Regular Q-learning,5,788,0.050999999046325684
Regular Q-learning,5,789,0.0560000017285347
Regular Q-learning,5,790,0.04800000041723251
Regular Q-learning,5,791,0.04699999839067459
Regular Q-learning,5,792,0.05000000074505806
Regular Q-learning,5,793,0.05700000002980232
Regular Q-learning,5,794,0.04899999871850014
Regular Q-learning,5,795,0.04800000041723251
Regular Q-learning,5,796,0.04800000041723251
Regular Q-learning,5,797,0.0560000017285347
Regular Q-learning,5,798,0.04899999871850014
Regular Q-learning,5,799,0.04800000041723251
Regular Q-learning,5,800,0.04899999871850014
Regular Q-learning,5,801,0.0560000017285347
Regular Q-learning,5,802,0.04899999871850014
Regular Q-learning,5,803,0.052000001072883606
Regular Q-learning,5,804,0.04899999871850014
Regular Q-learning,5,805,0.054999999701976776
Regular Q-learning,5,806,0.05000000074505806
Regular Q-learning,5,807,0.04800000041723251
Regular Q-learning,5,808,0.04899999871850014
Regular Q-learning,5,809,0.05400000140070915
Regular Q-learning,5,810,0.04899999871850014
Regular Q-learning,5,811,0.05000000074505806
Regular Q-learning,5,812,0.04800000041723251
Regular Q-learning,5,813,0.05400000140070915
Regular Q-learning,5,814,0.04899999871850014
Regular Q-learning,5,815,0.05000000074505806
Regular Q-learning,5,816,0.04800000041723251
Regular Q-learning,5,817,0.05400000140070915
Regular Q-learning,5,818,0.052000001072883606
Regular Q-learning,5,819,0.05000000074505806
Regular Q-learning,5,820,0.04899999871850014
Regular Q-learning,5,821,0.05400000140070915
Regular Q-learning,5,822,0.052000001072883606
Regular Q-learning,5,823,0.04800000041723251
Regular Q-learning,5,824,0.04899999871850014
Regular Q-learning,5,825,0.05299999937415123
Regular Q-learning,5,826,0.04899999871850014
Regular Q-learning,5,827,0.052000001072883606
Regular Q-learning,5,828,0.05000000074505806
Regular Q-learning,5,829,0.05400000140070915
Regular Q-learning,5,830,0.04699999839067459
Regular Q-learning,5,831,0.05000000074505806
Regular Q-learning,5,832,0.052000001072883606
Regular Q-learning,5,833,0.05400000140070915
Regular Q-learning,5,834,0.04699999839067459
Regular Q-learning,5,835,0.050999999046325684
Regular Q-learning,5,836,0.04899999871850014
Regular Q-learning,5,837,0.054999999701976776
Regular Q-learning,5,838,0.04699999839067459
Regular Q-learning,5,839,0.050999999046325684
Regular Q-learning,5,840,0.05000000074505806
Regular Q-learning,5,841,0.050999999046325684
Regular Q-learning,5,842,0.04699999839067459
Regular Q-learning,5,843,0.052000001072883606
Regular Q-learning,5,844,0.050999999046325684
Regular Q-learning,5,845,0.04899999871850014
Regular Q-learning,5,846,0.04699999839067459
Regular Q-learning,5,847,0.05400000140070915
Regular Q-learning,5,848,0.04800000041723251
Regular Q-learning,5,849,0.05000000074505806
Regular Q-learning,5,850,0.04899999871850014
Regular Q-learning,5,851,0.052000001072883606
Regular Q-learning,5,852,0.052000001072883606
Regular Q-learning,5,853,0.04699999839067459
Regular Q-learning,5,854,0.050999999046325684
Regular Q-learning,5,855,0.04899999871850014
Regular Q-learning,5,856,0.050999999046325684
Regular Q-learning,5,857,0.04800000041723251
Regular Q-learning,5,858,0.05000000074505806
Regular Q-learning,5,859,0.05299999937415123
Regular Q-learning,5,860,0.050999999046325684
Regular Q-learning,5,861,0.05000000074505806
Regular Q-learning,5,862,0.04800000041723251
Regular Q-learning,5,863,0.05400000140070915
Regular Q-learning,5,864,0.050999999046325684
Regular Q-learning,5,865,0.050999999046325684
Regular Q-learning,5,866,0.04500000178813934
Regular Q-learning,5,867,0.050999999046325684
Regular Q-learning,5,868,0.05299999937415123
Regular Q-learning,5,869,0.052000001072883606
Regular Q-learning,5,870,0.04500000178813934
Regular Q-learning,5,871,0.05000000074505806
Regular Q-learning,5,872,0.050999999046325684
Regular Q-learning,5,873,0.050999999046325684
Regular Q-learning,5,874,0.04699999839067459
Regular Q-learning,5,875,0.052000001072883606
Regular Q-learning,5,876,0.05299999937415123
Regular Q-learning,5,877,0.05000000074505806
Regular Q-learning,5,878,0.04500000178813934
Regular Q-learning,5,879,0.05000000074505806
Regular Q-learning,5,880,0.05299999937415123
Regular Q-learning,5,881,0.04899999871850014
Regular Q-learning,5,882,0.04899999871850014
Regular Q-learning,5,883,0.050999999046325684
Regular Q-learning,5,884,0.050999999046325684
Regular Q-learning,5,885,0.05299999937415123
Regular Q-learning,5,886,0.04699999839067459
Regular Q-learning,5,887,0.04800000041723251
Regular Q-learning,5,888,0.050999999046325684
Regular Q-learning,5,889,0.052000001072883606
Regular Q-learning,5,890,0.04899999871850014
Regular Q-learning,5,891,0.05000000074505806
Regular Q-learning,5,892,0.04800000041723251
Regular Q-learning,5,893,0.050999999046325684
Regular Q-learning,5,894,0.04899999871850014
Regular Q-learning,5,895,0.050999999046325684
Regular Q-learning,5,896,0.05000000074505806
Regular Q-learning,5,897,0.050999999046325684
Regular Q-learning,5,898,0.04800000041723251
Regular Q-learning,5,899,0.052000001072883606
Regular Q-learning,5,900,0.04800000041723251
Regular Q-learning,5,901,0.050999999046325684
Regular Q-learning,5,902,0.04699999839067459
Regular Q-learning,5,903,0.050999999046325684
Regular Q-learning,5,904,0.05000000074505806
Regular Q-learning,5,905,0.05000000074505806
Regular Q-learning,5,906,0.04899999871850014
Regular Q-learning,5,907,0.05000000074505806
Regular Q-learning,5,908,0.04600000008940697
Regular Q-learning,5,909,0.052000001072883606
Regular Q-learning,5,910,0.04699999839067459
Regular Q-learning,5,911,0.052000001072883606
Regular Q-learning,5,912,0.04800000041723251
Regular Q-learning,5,913,0.05000000074505806
Regular Q-learning,5,914,0.04800000041723251
Regular Q-learning,5,915,0.05400000140070915
Regular Q-learning,5,916,0.04800000041723251
Regular Q-learning,5,917,0.04899999871850014
Regular Q-learning,5,918,0.04800000041723251
Regular Q-learning,5,919,0.04899999871850014
Regular Q-learning,5,920,0.04800000041723251
Regular Q-learning,5,921,0.04899999871850014
Regular Q-learning,5,922,0.04899999871850014
Regular Q-learning,5,923,0.04800000041723251
Regular Q-learning,5,924,0.04800000041723251
Regular Q-learning,5,925,0.052000001072883606
Regular Q-learning,5,926,0.050999999046325684
Regular Q-learning,5,927,0.04600000008940697
Regular Q-learning,5,928,0.04899999871850014
Regular Q-learning,5,929,0.04899999871850014
Regular Q-learning,5,930,0.04800000041723251
Regular Q-learning,5,931,0.04699999839067459
Regular Q-learning,5,932,0.05000000074505806
Regular Q-learning,5,933,0.04800000041723251
Regular Q-learning,5,934,0.04899999871850014
Regular Q-learning,5,935,0.04899999871850014
Regular Q-learning,5,936,0.04899999871850014
Regular Q-learning,5,937,0.04600000008940697
Regular Q-learning,5,938,0.04899999871850014
Regular Q-learning,5,939,0.04800000041723251
Regular Q-learning,5,940,0.04899999871850014
Regular Q-learning,5,941,0.04800000041723251
Regular Q-learning,5,942,0.04800000041723251
Regular Q-learning,5,943,0.04699999839067459
Regular Q-learning,5,944,0.04899999871850014
Regular Q-learning,5,945,0.04899999871850014
Regular Q-learning,5,946,0.04899999871850014
Regular Q-learning,5,947,0.04800000041723251
Regular Q-learning,5,948,0.04800000041723251
Regular Q-learning,5,949,0.04800000041723251
Regular Q-learning,5,950,0.04899999871850014
Regular Q-learning,5,951,0.04699999839067459
Regular Q-learning,5,952,0.04899999871850014
Regular Q-learning,5,953,0.04800000041723251
Regular Q-learning,5,954,0.04800000041723251
Regular Q-learning,5,955,0.04800000041723251
Regular Q-learning,5,956,0.04899999871850014
Regular Q-learning,5,957,0.04899999871850014
Regular Q-learning,5,958,0.04699999839067459
Regular Q-learning,5,959,0.04800000041723251
Regular Q-learning,5,960,0.05000000074505806
Regular Q-learning,5,961,0.05000000074505806
Regular Q-learning,5,962,0.04899999871850014
Regular Q-learning,5,963,0.04699999839067459
Regular Q-learning,5,964,0.04600000008940697
Regular Q-learning,5,965,0.05299999937415123
Regular Q-learning,5,966,0.04800000041723251
Regular Q-learning,5,967,0.04699999839067459
Regular Q-learning,5,968,0.04600000008940697
Regular Q-learning,5,969,0.052000001072883606
Regular Q-learning,5,970,0.04800000041723251
Regular Q-learning,5,971,0.04699999839067459
Regular Q-learning,5,972,0.04699999839067459
Regular Q-learning,5,973,0.05299999937415123
Regular Q-learning,5,974,0.04800000041723251
Regular Q-learning,5,975,0.04699999839067459
Regular Q-learning,5,976,0.04699999839067459
Regular Q-learning,5,977,0.050999999046325684
Regular Q-learning,5,978,0.04600000008940697
Regular Q-learning,5,979,0.04699999839067459
Regular Q-learning,5,980,0.04899999871850014
Regular Q-learning,5,981,0.05299999937415123
Regular Q-learning,5,982,0.04699999839067459
Regular Q-learning,5,983,0.04699999839067459
Regular Q-learning,5,984,0.04899999871850014
Regular Q-learning,5,985,0.052000001072883606
Regular Q-learning,5,986,0.04800000041723251
Regular Q-learning,5,987,0.04600000008940697
Regular Q-learning,5,988,0.04699999839067459
Regular Q-learning,5,989,0.05400000140070915
Regular Q-learning,5,990,0.04800000041723251
Regular Q-learning,5,991,0.04800000041723251
Regular Q-learning,5,992,0.04500000178813934
Regular Q-learning,5,993,0.05400000140070915
Regular Q-learning,5,994,0.04699999839067459
Regular Q-learning,5,995,0.04699999839067459
Regular Q-learning,5,996,0.04500000178813934
Regular Q-learning,5,997,0.052000001072883606
Regular Q-learning,5,998,0.05000000074505806
Regular Q-learning,5,999,0.04600000008940697
Regular Q-learning,5,1000,0.04699999839067459
Regular Q-learning,10,1,0.23999999463558197
Regular Q-learning,10,2,0.18700000643730164
Regular Q-learning,10,3,0.1459999978542328
Regular Q-learning,10,4,0.12700000405311584
Regular Q-learning,10,5,0.11500000208616257
Regular Q-learning,10,6,0.11400000005960464
Regular Q-learning,10,7,0.10100000351667404
Regular Q-learning,10,8,0.11599999666213989
Regular Q-learning,10,9,0.0989999994635582
Regular Q-learning,10,10,0.1080000028014183
Regular Q-learning,10,11,0.11400000005960464
Regular Q-learning,10,12,0.11100000143051147
Regular Q-learning,10,13,0.09700000286102295
Regular Q-learning,10,14,0.125
Regular Q-learning,10,15,0.12099999934434891
Regular Q-learning,10,16,0.12099999934434891
Regular Q-learning,10,17,0.11999999731779099
Regular Q-learning,10,18,0.12700000405311584
Regular Q-learning,10,19,0.11299999803304672
Regular Q-learning,10,20,0.11599999666213989
Regular Q-learning,10,21,0.10499999672174454
Regular Q-learning,10,22,0.11699999868869781
Regular Q-learning,10,23,0.10300000011920929
Regular Q-learning,10,24,0.11599999666213989
Regular Q-learning,10,25,0.11100000143051147
Regular Q-learning,10,26,0.1080000028014183
Regular Q-learning,10,27,0.10100000351667404
Regular Q-learning,10,28,0.10199999809265137
Regular Q-learning,10,29,0.10499999672174454
Regular Q-learning,10,30,0.10499999672174454
Regular Q-learning,10,31,0.09300000220537186
Regular Q-learning,10,32,0.09399999678134918
Regular Q-learning,10,33,0.09300000220537186
Regular Q-learning,10,34,0.10000000149011612
Regular Q-learning,10,35,0.08799999952316284
Regular Q-learning,10,36,0.08900000154972076
Regular Q-learning,10,37,0.08699999749660492
Regular Q-learning,10,38,0.07400000095367432
Regular Q-learning,10,39,0.0820000022649765
Regular Q-learning,10,40,0.08100000023841858
Regular Q-learning,10,41,0.0860000029206276
Regular Q-learning,10,42,0.07599999755620956
Regular Q-learning,10,43,0.07699999958276749
Regular Q-learning,10,44,0.07000000029802322
Regular Q-learning,10,45,0.08500000089406967
Regular Q-learning,10,46,0.07199999690055847
Regular Q-learning,10,47,0.07900000363588333
Regular Q-learning,10,48,0.06300000101327896
Regular Q-learning,10,49,0.07100000232458115
Regular Q-learning,10,50,0.0689999982714653
Regular Q-learning,10,51,0.07400000095367432
Regular Q-learning,10,52,0.057999998331069946
Regular Q-learning,10,53,0.06700000166893005
Regular Q-learning,10,54,0.06199999898672104
Regular Q-learning,10,55,0.07100000232458115
Regular Q-learning,10,56,0.05700000002980232
Regular Q-learning,10,57,0.06199999898672104
Regular Q-learning,10,58,0.054999999701976776
Regular Q-learning,10,59,0.06400000303983688
Regular Q-learning,10,60,0.05299999937415123
Regular Q-learning,10,61,0.052000001072883606
Regular Q-learning,10,62,0.05000000074505806
Regular Q-learning,10,63,0.0560000017285347
Regular Q-learning,10,64,0.04800000041723251
Regular Q-learning,10,65,0.06199999898672104
Regular Q-learning,10,66,0.05999999865889549
Regular Q-learning,10,67,0.061000000685453415
Regular Q-learning,10,68,0.054999999701976776
Regular Q-learning,10,69,0.05900000035762787
Regular Q-learning,10,70,0.05000000074505806
Regular Q-learning,10,71,0.05999999865889549
Regular Q-learning,10,72,0.04600000008940697
Regular Q-learning,10,73,0.05299999937415123
Regular Q-learning,10,74,0.05400000140070915
Regular Q-learning,10,75,0.05700000002980232
Regular Q-learning,10,76,0.04800000041723251
Regular Q-learning,10,77,0.05700000002980232
Regular Q-learning,10,78,0.050999999046325684
Regular Q-learning,10,79,0.0560000017285347
Regular Q-learning,10,80,0.05000000074505806
Regular Q-learning,10,81,0.05700000002980232
Regular Q-learning,10,82,0.04500000178813934
Regular Q-learning,10,83,0.054999999701976776
Regular Q-learning,10,84,0.04899999871850014
Regular Q-learning,10,85,0.05700000002980232
Regular Q-learning,10,86,0.04699999839067459
Regular Q-learning,10,87,0.05700000002980232
Regular Q-learning,10,88,0.04600000008940697
Regular Q-learning,10,89,0.05000000074505806
Regular Q-learning,10,90,0.04699999839067459
Regular Q-learning,10,91,0.050999999046325684
Regular Q-learning,10,92,0.0430000014603138
Regular Q-learning,10,93,0.05400000140070915
Regular Q-learning,10,94,0.03700000047683716
Regular Q-learning,10,95,0.05400000140070915
Regular Q-learning,10,96,0.04100000113248825
Regular Q-learning,10,97,0.0560000017285347
Regular Q-learning,10,98,0.041999999433755875
Regular Q-learning,10,99,0.05400000140070915
Regular Q-learning,10,100,0.041999999433755875
Regular Q-learning,10,101,0.04600000008940697
Regular Q-learning,10,102,0.0430000014603138
Regular Q-learning,10,103,0.04699999839067459
Regular Q-learning,10,104,0.03999999910593033
Regular Q-learning,10,105,0.04800000041723251
Regular Q-learning,10,106,0.04500000178813934
Regular Q-learning,10,107,0.050999999046325684
Regular Q-learning,10,108,0.041999999433755875
Regular Q-learning,10,109,0.05000000074505806
Regular Q-learning,10,110,0.035999998450279236
Regular Q-learning,10,111,0.050999999046325684
Regular Q-learning,10,112,0.03799999877810478
Regular Q-learning,10,113,0.04699999839067459
Regular Q-learning,10,114,0.039000000804662704
Regular Q-learning,10,115,0.050999999046325684
Regular Q-learning,10,116,0.04399999976158142
Regular Q-learning,10,117,0.04100000113248825
Regular Q-learning,10,118,0.03500000014901161
Regular Q-learning,10,119,0.052000001072883606
Regular Q-learning,10,120,0.039000000804662704
Regular Q-learning,10,121,0.04500000178813934
Regular Q-learning,10,122,0.03700000047683716
Regular Q-learning,10,123,0.05000000074505806
Regular Q-learning,10,124,0.03999999910593033
Regular Q-learning,10,125,0.04600000008940697
Regular Q-learning,10,126,0.03799999877810478
Regular Q-learning,10,127,0.04699999839067459
Regular Q-learning,10,128,0.03999999910593033
Regular Q-learning,10,129,0.04100000113248825
Regular Q-learning,10,130,0.03500000014901161
Regular Q-learning,10,131,0.04800000041723251
Regular Q-learning,10,132,0.03700000047683716
Regular Q-learning,10,133,0.04899999871850014
Regular Q-learning,10,134,0.03700000047683716
Regular Q-learning,10,135,0.04899999871850014
Regular Q-learning,10,136,0.039000000804662704
Regular Q-learning,10,137,0.04500000178813934
Regular Q-learning,10,138,0.03500000014901161
Regular Q-learning,10,139,0.04800000041723251
Regular Q-learning,10,140,0.03799999877810478
Regular Q-learning,10,141,0.04899999871850014
Regular Q-learning,10,142,0.035999998450279236
Regular Q-learning,10,143,0.04800000041723251
Regular Q-learning,10,144,0.035999998450279236
Regular Q-learning,10,145,0.04600000008940697
Regular Q-learning,10,146,0.032999999821186066
Regular Q-learning,10,147,0.0430000014603138
Regular Q-learning,10,148,0.03400000184774399
Regular Q-learning,10,149,0.04699999839067459
Regular Q-learning,10,150,0.03700000047683716
Regular Q-learning,10,151,0.04500000178813934
Regular Q-learning,10,152,0.03500000014901161
Regular Q-learning,10,153,0.04699999839067459
Regular Q-learning,10,154,0.03500000014901161
Regular Q-learning,10,155,0.041999999433755875
Regular Q-learning,10,156,0.035999998450279236
Regular Q-learning,10,157,0.04500000178813934
Regular Q-learning,10,158,0.03500000014901161
Regular Q-learning,10,159,0.0430000014603138
Regular Q-learning,10,160,0.03700000047683716
Regular Q-learning,10,161,0.04399999976158142
Regular Q-learning,10,162,0.03500000014901161
Regular Q-learning,10,163,0.04500000178813934
Regular Q-learning,10,164,0.03799999877810478
Regular Q-learning,10,165,0.04600000008940697
Regular Q-learning,10,166,0.032999999821186066
Regular Q-learning,10,167,0.04399999976158142
Regular Q-learning,10,168,0.035999998450279236
Regular Q-learning,10,169,0.04600000008940697
Regular Q-learning,10,170,0.035999998450279236
Regular Q-learning,10,171,0.041999999433755875
Regular Q-learning,10,172,0.03500000014901161
Regular Q-learning,10,173,0.04899999871850014
Regular Q-learning,10,174,0.03500000014901161
Regular Q-learning,10,175,0.04500000178813934
Regular Q-learning,10,176,0.03999999910593033
Regular Q-learning,10,177,0.03799999877810478
Regular Q-learning,10,178,0.035999998450279236
Regular Q-learning,10,179,0.04899999871850014
Regular Q-learning,10,180,0.03400000184774399
Regular Q-learning,10,181,0.04399999976158142
Regular Q-learning,10,182,0.03500000014901161
Regular Q-learning,10,183,0.039000000804662704
Regular Q-learning,10,184,0.03400000184774399
Regular Q-learning,10,185,0.04500000178813934
Regular Q-learning,10,186,0.03400000184774399
Regular Q-learning,10,187,0.04500000178813934
Regular Q-learning,10,188,0.035999998450279236
Regular Q-learning,10,189,0.04100000113248825
Regular Q-learning,10,190,0.03400000184774399
Regular Q-learning,10,191,0.0430000014603138
Regular Q-learning,10,192,0.03799999877810478
Regular Q-learning,10,193,0.041999999433755875
Regular Q-learning,10,194,0.035999998450279236
Regular Q-learning,10,195,0.04399999976158142
Regular Q-learning,10,196,0.0430000014603138
Regular Q-learning,10,197,0.04100000113248825
Regular Q-learning,10,198,0.035999998450279236
Regular Q-learning,10,199,0.041999999433755875
Regular Q-learning,10,200,0.035999998450279236
Regular Q-learning,10,201,0.035999998450279236
Regular Q-learning,10,202,0.035999998450279236
Regular Q-learning,10,203,0.04399999976158142
Regular Q-learning,10,204,0.03700000047683716
Regular Q-learning,10,205,0.041999999433755875
Regular Q-learning,10,206,0.035999998450279236
Regular Q-learning,10,207,0.041999999433755875
Regular Q-learning,10,208,0.03799999877810478
Regular Q-learning,10,209,0.04800000041723251
Regular Q-learning,10,210,0.03799999877810478
Regular Q-learning,10,211,0.04399999976158142
Regular Q-learning,10,212,0.039000000804662704
Regular Q-learning,10,213,0.041999999433755875
Regular Q-learning,10,214,0.03099999949336052
Regular Q-learning,10,215,0.04699999839067459
Regular Q-learning,10,216,0.03500000014901161
Regular Q-learning,10,217,0.041999999433755875
Regular Q-learning,10,218,0.03799999877810478
Regular Q-learning,10,219,0.04100000113248825
Regular Q-learning,10,220,0.03799999877810478
Regular Q-learning,10,221,0.04100000113248825
Regular Q-learning,10,222,0.03700000047683716
Regular Q-learning,10,223,0.0430000014603138
Regular Q-learning,10,224,0.035999998450279236
Regular Q-learning,10,225,0.03999999910593033
Regular Q-learning,10,226,0.03799999877810478
Regular Q-learning,10,227,0.0430000014603138
Regular Q-learning,10,228,0.03400000184774399
Regular Q-learning,10,229,0.03799999877810478
Regular Q-learning,10,230,0.032999999821186066
Regular Q-learning,10,231,0.0430000014603138
Regular Q-learning,10,232,0.03799999877810478
Regular Q-learning,10,233,0.03799999877810478
Regular Q-learning,10,234,0.03799999877810478
Regular Q-learning,10,235,0.039000000804662704
Regular Q-learning,10,236,0.03999999910593033
Regular Q-learning,10,237,0.03400000184774399
Regular Q-learning,10,238,0.03700000047683716
Regular Q-learning,10,239,0.03999999910593033
Regular Q-learning,10,240,0.03799999877810478
Regular Q-learning,10,241,0.03700000047683716
Regular Q-learning,10,242,0.039000000804662704
Regular Q-learning,10,243,0.0430000014603138
Regular Q-learning,10,244,0.03700000047683716
Regular Q-learning,10,245,0.03799999877810478
Regular Q-learning,10,246,0.03700000047683716
Regular Q-learning,10,247,0.041999999433755875
Regular Q-learning,10,248,0.03700000047683716
Regular Q-learning,10,249,0.032999999821186066
Regular Q-learning,10,250,0.03799999877810478
Regular Q-learning,10,251,0.04100000113248825
Regular Q-learning,10,252,0.03200000151991844
Regular Q-learning,10,253,0.04100000113248825
Regular Q-learning,10,254,0.032999999821186066
Regular Q-learning,10,255,0.04100000113248825
Regular Q-learning,10,256,0.032999999821186066
Regular Q-learning,10,257,0.035999998450279236
Regular Q-learning,10,258,0.035999998450279236
Regular Q-learning,10,259,0.04100000113248825
Regular Q-learning,10,260,0.03200000151991844
Regular Q-learning,10,261,0.03799999877810478
Regular Q-learning,10,262,0.03200000151991844
Regular Q-learning,10,263,0.04600000008940697
Regular Q-learning,10,264,0.03799999877810478
Regular Q-learning,10,265,0.03500000014901161
Regular Q-learning,10,266,0.03400000184774399
Regular Q-learning,10,267,0.041999999433755875
Regular Q-learning,10,268,0.03799999877810478
Regular Q-learning,10,269,0.03799999877810478
Regular Q-learning,10,270,0.032999999821186066
Regular Q-learning,10,271,0.04100000113248825
Regular Q-learning,10,272,0.035999998450279236
Regular Q-learning,10,273,0.035999998450279236
Regular Q-learning,10,274,0.03500000014901161
Regular Q-learning,10,275,0.0430000014603138
Regular Q-learning,10,276,0.03500000014901161
Regular Q-learning,10,277,0.03799999877810478
Regular Q-learning,10,278,0.032999999821186066
Regular Q-learning,10,279,0.04100000113248825
Regular Q-learning,10,280,0.03400000184774399
Regular Q-learning,10,281,0.03500000014901161
Regular Q-learning,10,282,0.032999999821186066
Regular Q-learning,10,283,0.03700000047683716
Regular Q-learning,10,284,0.032999999821186066
Regular Q-learning,10,285,0.04100000113248825
Regular Q-learning,10,286,0.03200000151991844
Regular Q-learning,10,287,0.041999999433755875
Regular Q-learning,10,288,0.03799999877810478
Regular Q-learning,10,289,0.03799999877810478
Regular Q-learning,10,290,0.03200000151991844
Regular Q-learning,10,291,0.0430000014603138
Regular Q-learning,10,292,0.028999999165534973
Regular Q-learning,10,293,0.03999999910593033
Regular Q-learning,10,294,0.035999998450279236
Regular Q-learning,10,295,0.03799999877810478
Regular Q-learning,10,296,0.02800000086426735
Regular Q-learning,10,297,0.03999999910593033
Regular Q-learning,10,298,0.035999998450279236
Regular Q-learning,10,299,0.03999999910593033
Regular Q-learning,10,300,0.028999999165534973
Regular Q-learning,10,301,0.04100000113248825
Regular Q-learning,10,302,0.03500000014901161
Regular Q-learning,10,303,0.03700000047683716
Regular Q-learning,10,304,0.029999999329447746
Regular Q-learning,10,305,0.03700000047683716
Regular Q-learning,10,306,0.03500000014901161
Regular Q-learning,10,307,0.041999999433755875
Regular Q-learning,10,308,0.027000000700354576
Regular Q-learning,10,309,0.03999999910593033
Regular Q-learning,10,310,0.03200000151991844
Regular Q-learning,10,311,0.03799999877810478
Regular Q-learning,10,312,0.03099999949336052
Regular Q-learning,10,313,0.039000000804662704
Regular Q-learning,10,314,0.032999999821186066
Regular Q-learning,10,315,0.04100000113248825
Regular Q-learning,10,316,0.029999999329447746
Regular Q-learning,10,317,0.035999998450279236
Regular Q-learning,10,318,0.03400000184774399
Regular Q-learning,10,319,0.03999999910593033
Regular Q-learning,10,320,0.029999999329447746
Regular Q-learning,10,321,0.03500000014901161
Regular Q-learning,10,322,0.03099999949336052
Regular Q-learning,10,323,0.03999999910593033
Regular Q-learning,10,324,0.035999998450279236
Regular Q-learning,10,325,0.032999999821186066
Regular Q-learning,10,326,0.03099999949336052
Regular Q-learning,10,327,0.04100000113248825
Regular Q-learning,10,328,0.03200000151991844
Regular Q-learning,10,329,0.03500000014901161
Regular Q-learning,10,330,0.03200000151991844
Regular Q-learning,10,331,0.03500000014901161
Regular Q-learning,10,332,0.032999999821186066
Regular Q-learning,10,333,0.03500000014901161
Regular Q-learning,10,334,0.032999999821186066
Regular Q-learning,10,335,0.03400000184774399
Regular Q-learning,10,336,0.03200000151991844
Regular Q-learning,10,337,0.035999998450279236
Regular Q-learning,10,338,0.029999999329447746
Regular Q-learning,10,339,0.03799999877810478
Regular Q-learning,10,340,0.035999998450279236
Regular Q-learning,10,341,0.03700000047683716
Regular Q-learning,10,342,0.032999999821186066
Regular Q-learning,10,343,0.035999998450279236
Regular Q-learning,10,344,0.03200000151991844
Regular Q-learning,10,345,0.035999998450279236
Regular Q-learning,10,346,0.028999999165534973
Regular Q-learning,10,347,0.03700000047683716
Regular Q-learning,10,348,0.03500000014901161
Regular Q-learning,10,349,0.03500000014901161
Regular Q-learning,10,350,0.029999999329447746
Regular Q-learning,10,351,0.03999999910593033
Regular Q-learning,10,352,0.029999999329447746
Regular Q-learning,10,353,0.03200000151991844
Regular Q-learning,10,354,0.02800000086426735
Regular Q-learning,10,355,0.03500000014901161
Regular Q-learning,10,356,0.03200000151991844
Regular Q-learning,10,357,0.035999998450279236
Regular Q-learning,10,358,0.029999999329447746
Regular Q-learning,10,359,0.03700000047683716
Regular Q-learning,10,360,0.03500000014901161
Regular Q-learning,10,361,0.03500000014901161
Regular Q-learning,10,362,0.02800000086426735
Regular Q-learning,10,363,0.041999999433755875
Regular Q-learning,10,364,0.029999999329447746
Regular Q-learning,10,365,0.03200000151991844
Regular Q-learning,10,366,0.03099999949336052
Regular Q-learning,10,367,0.03999999910593033
Regular Q-learning,10,368,0.032999999821186066
Regular Q-learning,10,369,0.028999999165534973
Regular Q-learning,10,370,0.028999999165534973
Regular Q-learning,10,371,0.03700000047683716
Regular Q-learning,10,372,0.032999999821186066
Regular Q-learning,10,373,0.032999999821186066
Regular Q-learning,10,374,0.03099999949336052
Regular Q-learning,10,375,0.03799999877810478
Regular Q-learning,10,376,0.03400000184774399
Regular Q-learning,10,377,0.029999999329447746
Regular Q-learning,10,378,0.03099999949336052
Regular Q-learning,10,379,0.03799999877810478
Regular Q-learning,10,380,0.03200000151991844
Regular Q-learning,10,381,0.028999999165534973
Regular Q-learning,10,382,0.032999999821186066
Regular Q-learning,10,383,0.035999998450279236
Regular Q-learning,10,384,0.03500000014901161
Regular Q-learning,10,385,0.02800000086426735
Regular Q-learning,10,386,0.03099999949336052
Regular Q-learning,10,387,0.03700000047683716
Regular Q-learning,10,388,0.03099999949336052
Regular Q-learning,10,389,0.03400000184774399
Regular Q-learning,10,390,0.029999999329447746
Regular Q-learning,10,391,0.03799999877810478
Regular Q-learning,10,392,0.03500000014901161
Regular Q-learning,10,393,0.03200000151991844
Regular Q-learning,10,394,0.03099999949336052
Regular Q-learning,10,395,0.03500000014901161
Regular Q-learning,10,396,0.03099999949336052
Regular Q-learning,10,397,0.03200000151991844
Regular Q-learning,10,398,0.028999999165534973
Regular Q-learning,10,399,0.04399999976158142
Regular Q-learning,10,400,0.03099999949336052
Regular Q-learning,10,401,0.03200000151991844
Regular Q-learning,10,402,0.027000000700354576
Regular Q-learning,10,403,0.039000000804662704
Regular Q-learning,10,404,0.03200000151991844
Regular Q-learning,10,405,0.035999998450279236
Regular Q-learning,10,406,0.02800000086426735
Regular Q-learning,10,407,0.03500000014901161
Regular Q-learning,10,408,0.03400000184774399
Regular Q-learning,10,409,0.03700000047683716
Regular Q-learning,10,410,0.02800000086426735
Regular Q-learning,10,411,0.03500000014901161
Regular Q-learning,10,412,0.03099999949336052
Regular Q-learning,10,413,0.039000000804662704
Regular Q-learning,10,414,0.026000000536441803
Regular Q-learning,10,415,0.03200000151991844
Regular Q-learning,10,416,0.03700000047683716
Regular Q-learning,10,417,0.035999998450279236
Regular Q-learning,10,418,0.028999999165534973
Regular Q-learning,10,419,0.032999999821186066
Regular Q-learning,10,420,0.03200000151991844
Regular Q-learning,10,421,0.03400000184774399
Regular Q-learning,10,422,0.028999999165534973
Regular Q-learning,10,423,0.03500000014901161
Regular Q-learning,10,424,0.028999999165534973
Regular Q-learning,10,425,0.03700000047683716
Regular Q-learning,10,426,0.029999999329447746
Regular Q-learning,10,427,0.03099999949336052
Regular Q-learning,10,428,0.029999999329447746
Regular Q-learning,10,429,0.035999998450279236
Regular Q-learning,10,430,0.029999999329447746
Regular Q-learning,10,431,0.03099999949336052
Regular Q-learning,10,432,0.029999999329447746
Regular Q-learning,10,433,0.03799999877810478
Regular Q-learning,10,434,0.029999999329447746
Regular Q-learning,10,435,0.03200000151991844
Regular Q-learning,10,436,0.02800000086426735
Regular Q-learning,10,437,0.035999998450279236
Regular Q-learning,10,438,0.028999999165534973
Regular Q-learning,10,439,0.032999999821186066
Regular Q-learning,10,440,0.032999999821186066
Regular Q-learning,10,441,0.03400000184774399
Regular Q-learning,10,442,0.027000000700354576
Regular Q-learning,10,443,0.03200000151991844
Regular Q-learning,10,444,0.02800000086426735
Regular Q-learning,10,445,0.03500000014901161
Regular Q-learning,10,446,0.03200000151991844
Regular Q-learning,10,447,0.03200000151991844
Regular Q-learning,10,448,0.028999999165534973
Regular Q-learning,10,449,0.03500000014901161
Regular Q-learning,10,450,0.03099999949336052
Regular Q-learning,10,451,0.03099999949336052
Regular Q-learning,10,452,0.028999999165534973
Regular Q-learning,10,453,0.03400000184774399
Regular Q-learning,10,454,0.029999999329447746
Regular Q-learning,10,455,0.03200000151991844
Regular Q-learning,10,456,0.02800000086426735
Regular Q-learning,10,457,0.03500000014901161
Regular Q-learning,10,458,0.03099999949336052
Regular Q-learning,10,459,0.03500000014901161
Regular Q-learning,10,460,0.027000000700354576
Regular Q-learning,10,461,0.03500000014901161
Regular Q-learning,10,462,0.029999999329447746
Regular Q-learning,10,463,0.03200000151991844
Regular Q-learning,10,464,0.03099999949336052
Regular Q-learning,10,465,0.03799999877810478
Regular Q-learning,10,466,0.02800000086426735
Regular Q-learning,10,467,0.029999999329447746
Regular Q-learning,10,468,0.027000000700354576
Regular Q-learning,10,469,0.03700000047683716
Regular Q-learning,10,470,0.027000000700354576
Regular Q-learning,10,471,0.032999999821186066
Regular Q-learning,10,472,0.02500000037252903
Regular Q-learning,10,473,0.03400000184774399
Regular Q-learning,10,474,0.02800000086426735
Regular Q-learning,10,475,0.03200000151991844
Regular Q-learning,10,476,0.024000000208616257
Regular Q-learning,10,477,0.03799999877810478
Regular Q-learning,10,478,0.028999999165534973
Regular Q-learning,10,479,0.03099999949336052
Regular Q-learning,10,480,0.024000000208616257
Regular Q-learning,10,481,0.03700000047683716
Regular Q-learning,10,482,0.032999999821186066
Regular Q-learning,10,483,0.032999999821186066
Regular Q-learning,10,484,0.024000000208616257
Regular Q-learning,10,485,0.03400000184774399
Regular Q-learning,10,486,0.03200000151991844
Regular Q-learning,10,487,0.03200000151991844
Regular Q-learning,10,488,0.023000000044703484
Regular Q-learning,10,489,0.03500000014901161
Regular Q-learning,10,490,0.032999999821186066
Regular Q-learning,10,491,0.03200000151991844
Regular Q-learning,10,492,0.02500000037252903
Regular Q-learning,10,493,0.03500000014901161
Regular Q-learning,10,494,0.032999999821186066
Regular Q-learning,10,495,0.03099999949336052
Regular Q-learning,10,496,0.026000000536441803
Regular Q-learning,10,497,0.032999999821186066
Regular Q-learning,10,498,0.03200000151991844
Regular Q-learning,10,499,0.029999999329447746
Regular Q-learning,10,500,0.026000000536441803
Regular Q-learning,10,501,0.03400000184774399
Regular Q-learning,10,502,0.03099999949336052
Regular Q-learning,10,503,0.028999999165534973
Regular Q-learning,10,504,0.02500000037252903
Regular Q-learning,10,505,0.03400000184774399
Regular Q-learning,10,506,0.03200000151991844
Regular Q-learning,10,507,0.029999999329447746
Regular Q-learning,10,508,0.02500000037252903
Regular Q-learning,10,509,0.03400000184774399
Regular Q-learning,10,510,0.032999999821186066
Regular Q-learning,10,511,0.03200000151991844
Regular Q-learning,10,512,0.026000000536441803
Regular Q-learning,10,513,0.03099999949336052
Regular Q-learning,10,514,0.029999999329447746
Regular Q-learning,10,515,0.032999999821186066
Regular Q-learning,10,516,0.026000000536441803
Regular Q-learning,10,517,0.03700000047683716
Regular Q-learning,10,518,0.02800000086426735
Regular Q-learning,10,519,0.029999999329447746
Regular Q-learning,10,520,0.027000000700354576
Regular Q-learning,10,521,0.03200000151991844
Regular Q-learning,10,522,0.029999999329447746
Regular Q-learning,10,523,0.03400000184774399
Regular Q-learning,10,524,0.02199999988079071
Regular Q-learning,10,525,0.032999999821186066
Regular Q-learning,10,526,0.028999999165534973
Regular Q-learning,10,527,0.035999998450279236
Regular Q-learning,10,528,0.02500000037252903
Regular Q-learning,10,529,0.032999999821186066
Regular Q-learning,10,530,0.02500000037252903
Regular Q-learning,10,531,0.03500000014901161
Regular Q-learning,10,532,0.026000000536441803
Regular Q-learning,10,533,0.03400000184774399
Regular Q-learning,10,534,0.023000000044703484
Regular Q-learning,10,535,0.035999998450279236
Regular Q-learning,10,536,0.024000000208616257
Regular Q-learning,10,537,0.032999999821186066
Regular Q-learning,10,538,0.023000000044703484
Regular Q-learning,10,539,0.03799999877810478
Regular Q-learning,10,540,0.027000000700354576
Regular Q-learning,10,541,0.03400000184774399
Regular Q-learning,10,542,0.019999999552965164
Regular Q-learning,10,543,0.03700000047683716
Regular Q-learning,10,544,0.02800000086426735
Regular Q-learning,10,545,0.03500000014901161
Regular Q-learning,10,546,0.02199999988079071
Regular Q-learning,10,547,0.035999998450279236
Regular Q-learning,10,548,0.026000000536441803
Regular Q-learning,10,549,0.035999998450279236
Regular Q-learning,10,550,0.027000000700354576
Regular Q-learning,10,551,0.03400000184774399
Regular Q-learning,10,552,0.026000000536441803
Regular Q-learning,10,553,0.03400000184774399
Regular Q-learning,10,554,0.026000000536441803
Regular Q-learning,10,555,0.032999999821186066
Regular Q-learning,10,556,0.028999999165534973
Regular Q-learning,10,557,0.032999999821186066
Regular Q-learning,10,558,0.02500000037252903
Regular Q-learning,10,559,0.03400000184774399
Regular Q-learning,10,560,0.02500000037252903
Regular Q-learning,10,561,0.03500000014901161
Regular Q-learning,10,562,0.02800000086426735
Regular Q-learning,10,563,0.03099999949336052
Regular Q-learning,10,564,0.03400000184774399
Regular Q-learning,10,565,0.032999999821186066
Regular Q-learning,10,566,0.027000000700354576
Regular Q-learning,10,567,0.03500000014901161
Regular Q-learning,10,568,0.029999999329447746
Regular Q-learning,10,569,0.03099999949336052
Regular Q-learning,10,570,0.027000000700354576
Regular Q-learning,10,571,0.03200000151991844
Regular Q-learning,10,572,0.029999999329447746
Regular Q-learning,10,573,0.029999999329447746
Regular Q-learning,10,574,0.02500000037252903
Regular Q-learning,10,575,0.03500000014901161
Regular Q-learning,10,576,0.03099999949336052
Regular Q-learning,10,577,0.028999999165534973
Regular Q-learning,10,578,0.024000000208616257
Regular Q-learning,10,579,0.03400000184774399
Regular Q-learning,10,580,0.03200000151991844
Regular Q-learning,10,581,0.02800000086426735
Regular Q-learning,10,582,0.024000000208616257
Regular Q-learning,10,583,0.03099999949336052
Regular Q-learning,10,584,0.03099999949336052
Regular Q-learning,10,585,0.029999999329447746
Regular Q-learning,10,586,0.02800000086426735
Regular Q-learning,10,587,0.032999999821186066
Regular Q-learning,10,588,0.029999999329447746
Regular Q-learning,10,589,0.029999999329447746
Regular Q-learning,10,590,0.026000000536441803
Regular Q-learning,10,591,0.03400000184774399
Regular Q-learning,10,592,0.029999999329447746
Regular Q-learning,10,593,0.027000000700354576
Regular Q-learning,10,594,0.029999999329447746
Regular Q-learning,10,595,0.03200000151991844
Regular Q-learning,10,596,0.02800000086426735
Regular Q-learning,10,597,0.029999999329447746
Regular Q-learning,10,598,0.029999999329447746
Regular Q-learning,10,599,0.03400000184774399
Regular Q-learning,10,600,0.02800000086426735
Regular Q-learning,10,601,0.03099999949336052
Regular Q-learning,10,602,0.02800000086426735
Regular Q-learning,10,603,0.032999999821186066
Regular Q-learning,10,604,0.026000000536441803
Regular Q-learning,10,605,0.03200000151991844
Regular Q-learning,10,606,0.027000000700354576
Regular Q-learning,10,607,0.03500000014901161
Regular Q-learning,10,608,0.02500000037252903
Regular Q-learning,10,609,0.03099999949336052
Regular Q-learning,10,610,0.026000000536441803
Regular Q-learning,10,611,0.03700000047683716
Regular Q-learning,10,612,0.026000000536441803
Regular Q-learning,10,613,0.03099999949336052
Regular Q-learning,10,614,0.02500000037252903
Regular Q-learning,10,615,0.03400000184774399
Regular Q-learning,10,616,0.026000000536441803
Regular Q-learning,10,617,0.03099999949336052
Regular Q-learning,10,618,0.026000000536441803
Regular Q-learning,10,619,0.035999998450279236
Regular Q-learning,10,620,0.026000000536441803
Regular Q-learning,10,621,0.03200000151991844
Regular Q-learning,10,622,0.02800000086426735
Regular Q-learning,10,623,0.03500000014901161
Regular Q-learning,10,624,0.024000000208616257
Regular Q-learning,10,625,0.03200000151991844
Regular Q-learning,10,626,0.029999999329447746
Regular Q-learning,10,627,0.03500000014901161
Regular Q-learning,10,628,0.023000000044703484
Regular Q-learning,10,629,0.03200000151991844
Regular Q-learning,10,630,0.029999999329447746
Regular Q-learning,10,631,0.03400000184774399
Regular Q-learning,10,632,0.023000000044703484
Regular Q-learning,10,633,0.035999998450279236
Regular Q-learning,10,634,0.03200000151991844
Regular Q-learning,10,635,0.03099999949336052
Regular Q-learning,10,636,0.020999999716877937
Regular Q-learning,10,637,0.035999998450279236
Regular Q-learning,10,638,0.03200000151991844
Regular Q-learning,10,639,0.028999999165534973
Regular Q-learning,10,640,0.023000000044703484
Regular Q-learning,10,641,0.03500000014901161
Regular Q-learning,10,642,0.03400000184774399
Regular Q-learning,10,643,0.027000000700354576
Regular Q-learning,10,644,0.023000000044703484
Regular Q-learning,10,645,0.035999998450279236
Regular Q-learning,10,646,0.03200000151991844
Regular Q-learning,10,647,0.028999999165534973
Regular Q-learning,10,648,0.023000000044703484
Regular Q-learning,10,649,0.03500000014901161
Regular Q-learning,10,650,0.03099999949336052
Regular Q-learning,10,651,0.028999999165534973
Regular Q-learning,10,652,0.023000000044703484
Regular Q-learning,10,653,0.035999998450279236
Regular Q-learning,10,654,0.032999999821186066
Regular Q-learning,10,655,0.03099999949336052
Regular Q-learning,10,656,0.023000000044703484
Regular Q-learning,10,657,0.03400000184774399
Regular Q-learning,10,658,0.03400000184774399
Regular Q-learning,10,659,0.029999999329447746
Regular Q-learning,10,660,0.02199999988079071
Regular Q-learning,10,661,0.03400000184774399
Regular Q-learning,10,662,0.03099999949336052
Regular Q-learning,10,663,0.028999999165534973
Regular Q-learning,10,664,0.023000000044703484
Regular Q-learning,10,665,0.032999999821186066
Regular Q-learning,10,666,0.03400000184774399
Regular Q-learning,10,667,0.03099999949336052
Regular Q-learning,10,668,0.020999999716877937
Regular Q-learning,10,669,0.03500000014901161
Regular Q-learning,10,670,0.03099999949336052
Regular Q-learning,10,671,0.03200000151991844
Regular Q-learning,10,672,0.019999999552965164
Regular Q-learning,10,673,0.035999998450279236
Regular Q-learning,10,674,0.03099999949336052
Regular Q-learning,10,675,0.029999999329447746
Regular Q-learning,10,676,0.02199999988079071
Regular Q-learning,10,677,0.03400000184774399
Regular Q-learning,10,678,0.03099999949336052
Regular Q-learning,10,679,0.03400000184774399
Regular Q-learning,10,680,0.023000000044703484
Regular Q-learning,10,681,0.032999999821186066
Regular Q-learning,10,682,0.029999999329447746
Regular Q-learning,10,683,0.032999999821186066
Regular Q-learning,10,684,0.023000000044703484
Regular Q-learning,10,685,0.03500000014901161
Regular Q-learning,10,686,0.027000000700354576
Regular Q-learning,10,687,0.03200000151991844
Regular Q-learning,10,688,0.026000000536441803
Regular Q-learning,10,689,0.03400000184774399
Regular Q-learning,10,690,0.027000000700354576
Regular Q-learning,10,691,0.03099999949336052
Regular Q-learning,10,692,0.027000000700354576
Regular Q-learning,10,693,0.032999999821186066
Regular Q-learning,10,694,0.026000000536441803
Regular Q-learning,10,695,0.03099999949336052
Regular Q-learning,10,696,0.027000000700354576
Regular Q-learning,10,697,0.032999999821186066
Regular Q-learning,10,698,0.027000000700354576
Regular Q-learning,10,699,0.028999999165534973
Regular Q-learning,10,700,0.027000000700354576
Regular Q-learning,10,701,0.03200000151991844
Regular Q-learning,10,702,0.02800000086426735
Regular Q-learning,10,703,0.032999999821186066
Regular Q-learning,10,704,0.02500000037252903
Regular Q-learning,10,705,0.03400000184774399
Regular Q-learning,10,706,0.02500000037252903
Regular Q-learning,10,707,0.03400000184774399
Regular Q-learning,10,708,0.02500000037252903
Regular Q-learning,10,709,0.032999999821186066
Regular Q-learning,10,710,0.02800000086426735
Regular Q-learning,10,711,0.032999999821186066
Regular Q-learning,10,712,0.023000000044703484
Regular Q-learning,10,713,0.032999999821186066
Regular Q-learning,10,714,0.02199999988079071
Regular Q-learning,10,715,0.03400000184774399
Regular Q-learning,10,716,0.026000000536441803
Regular Q-learning,10,717,0.03200000151991844
Regular Q-learning,10,718,0.02500000037252903
Regular Q-learning,10,719,0.03200000151991844
Regular Q-learning,10,720,0.027000000700354576
Regular Q-learning,10,721,0.03500000014901161
Regular Q-learning,10,722,0.02500000037252903
Regular Q-learning,10,723,0.03400000184774399
Regular Q-learning,10,724,0.027000000700354576
Regular Q-learning,10,725,0.03400000184774399
Regular Q-learning,10,726,0.02500000037252903
Regular Q-learning,10,727,0.03099999949336052
Regular Q-learning,10,728,0.024000000208616257
Regular Q-learning,10,729,0.03200000151991844
Regular Q-learning,10,730,0.02800000086426735
Regular Q-learning,10,731,0.03500000014901161
Regular Q-learning,10,732,0.024000000208616257
Regular Q-learning,10,733,0.028999999165534973
Regular Q-learning,10,734,0.02500000037252903
Regular Q-learning,10,735,0.035999998450279236
Regular Q-learning,10,736,0.026000000536441803
Regular Q-learning,10,737,0.032999999821186066
Regular Q-learning,10,738,0.02800000086426735
Regular Q-learning,10,739,0.029999999329447746
Regular Q-learning,10,740,0.027000000700354576
Regular Q-learning,10,741,0.03400000184774399
Regular Q-learning,10,742,0.024000000208616257
Regular Q-learning,10,743,0.032999999821186066
Regular Q-learning,10,744,0.026000000536441803
Regular Q-learning,10,745,0.032999999821186066
Regular Q-learning,10,746,0.024000000208616257
Regular Q-learning,10,747,0.03500000014901161
Regular Q-learning,10,748,0.02500000037252903
Regular Q-learning,10,749,0.03500000014901161
Regular Q-learning,10,750,0.02199999988079071
Regular Q-learning,10,751,0.032999999821186066
Regular Q-learning,10,752,0.027000000700354576
Regular Q-learning,10,753,0.03400000184774399
Regular Q-learning,10,754,0.024000000208616257
Regular Q-learning,10,755,0.03200000151991844
Regular Q-learning,10,756,0.027000000700354576
Regular Q-learning,10,757,0.029999999329447746
Regular Q-learning,10,758,0.02800000086426735
Regular Q-learning,10,759,0.03200000151991844
Regular Q-learning,10,760,0.026000000536441803
Regular Q-learning,10,761,0.03099999949336052
Regular Q-learning,10,762,0.027000000700354576
Regular Q-learning,10,763,0.03500000014901161
Regular Q-learning,10,764,0.026000000536441803
Regular Q-learning,10,765,0.02800000086426735
Regular Q-learning,10,766,0.03099999949336052
Regular Q-learning,10,767,0.028999999165534973
Regular Q-learning,10,768,0.028999999165534973
Regular Q-learning,10,769,0.028999999165534973
Regular Q-learning,10,770,0.028999999165534973
Regular Q-learning,10,771,0.028999999165534973
Regular Q-learning,10,772,0.02800000086426735
Regular Q-learning,10,773,0.028999999165534973
Regular Q-learning,10,774,0.02800000086426735
Regular Q-learning,10,775,0.03099999949336052
Regular Q-learning,10,776,0.028999999165534973
Regular Q-learning,10,777,0.027000000700354576
Regular Q-learning,10,778,0.02800000086426735
Regular Q-learning,10,779,0.03200000151991844
Regular Q-learning,10,780,0.029999999329447746
Regular Q-learning,10,781,0.02500000037252903
Regular Q-learning,10,782,0.027000000700354576
Regular Q-learning,10,783,0.03200000151991844
Regular Q-learning,10,784,0.029999999329447746
Regular Q-learning,10,785,0.028999999165534973
Regular Q-learning,10,786,0.02800000086426735
Regular Q-learning,10,787,0.032999999821186066
Regular Q-learning,10,788,0.028999999165534973
Regular Q-learning,10,789,0.026000000536441803
Regular Q-learning,10,790,0.02800000086426735
Regular Q-learning,10,791,0.03099999949336052
Regular Q-learning,10,792,0.028999999165534973
Regular Q-learning,10,793,0.027000000700354576
Regular Q-learning,10,794,0.028999999165534973
Regular Q-learning,10,795,0.03099999949336052
Regular Q-learning,10,796,0.02800000086426735
Regular Q-learning,10,797,0.026000000536441803
Regular Q-learning,10,798,0.03099999949336052
Regular Q-learning,10,799,0.03099999949336052
Regular Q-learning,10,800,0.02800000086426735
Regular Q-learning,10,801,0.028999999165534973
Regular Q-learning,10,802,0.029999999329447746
Regular Q-learning,10,803,0.029999999329447746
Regular Q-learning,10,804,0.026000000536441803
Regular Q-learning,10,805,0.029999999329447746
Regular Q-learning,10,806,0.03099999949336052
Regular Q-learning,10,807,0.029999999329447746
Regular Q-learning,10,808,0.024000000208616257
Regular Q-learning,10,809,0.029999999329447746
Regular Q-learning,10,810,0.03099999949336052
Regular Q-learning,10,811,0.03099999949336052
Regular Q-learning,10,812,0.026000000536441803
Regular Q-learning,10,813,0.029999999329447746
Regular Q-learning,10,814,0.03200000151991844
Regular Q-learning,10,815,0.029999999329447746
Regular Q-learning,10,816,0.02800000086426735
Regular Q-learning,10,817,0.02800000086426735
Regular Q-learning,10,818,0.028999999165534973
Regular Q-learning,10,819,0.029999999329447746
Regular Q-learning,10,820,0.02500000037252903
Regular Q-learning,10,821,0.029999999329447746
Regular Q-learning,10,822,0.028999999165534973
Regular Q-learning,10,823,0.03200000151991844
Regular Q-learning,10,824,0.027000000700354576
Regular Q-learning,10,825,0.028999999165534973
Regular Q-learning,10,826,0.028999999165534973
Regular Q-learning,10,827,0.03099999949336052
Regular Q-learning,10,828,0.02800000086426735
Regular Q-learning,10,829,0.029999999329447746
Regular Q-learning,10,830,0.029999999329447746
Regular Q-learning,10,831,0.03099999949336052
Regular Q-learning,10,832,0.026000000536441803
Regular Q-learning,10,833,0.029999999329447746
Regular Q-learning,10,834,0.027000000700354576
Regular Q-learning,10,835,0.027000000700354576
Regular Q-learning,10,836,0.028999999165534973
Regular Q-learning,10,837,0.03200000151991844
Regular Q-learning,10,838,0.026000000536441803
Regular Q-learning,10,839,0.029999999329447746
Regular Q-learning,10,840,0.02800000086426735
Regular Q-learning,10,841,0.03200000151991844
Regular Q-learning,10,842,0.026000000536441803
Regular Q-learning,10,843,0.029999999329447746
Regular Q-learning,10,844,0.02800000086426735
Regular Q-learning,10,845,0.032999999821186066
Regular Q-learning,10,846,0.026000000536441803
Regular Q-learning,10,847,0.03099999949336052
Regular Q-learning,10,848,0.026000000536441803
Regular Q-learning,10,849,0.03099999949336052
Regular Q-learning,10,850,0.02500000037252903
Regular Q-learning,10,851,0.03200000151991844
Regular Q-learning,10,852,0.026000000536441803
Regular Q-learning,10,853,0.032999999821186066
Regular Q-learning,10,854,0.02500000037252903
Regular Q-learning,10,855,0.028999999165534973
Regular Q-learning,10,856,0.027000000700354576
Regular Q-learning,10,857,0.03400000184774399
Regular Q-learning,10,858,0.024000000208616257
Regular Q-learning,10,859,0.028999999165534973
Regular Q-learning,10,860,0.027000000700354576
Regular Q-learning,10,861,0.03099999949336052
Regular Q-learning,10,862,0.02800000086426735
Regular Q-learning,10,863,0.029999999329447746
Regular Q-learning,10,864,0.02800000086426735
Regular Q-learning,10,865,0.03200000151991844
Regular Q-learning,10,866,0.02800000086426735
Regular Q-learning,10,867,0.02800000086426735
Regular Q-learning,10,868,0.028999999165534973
Regular Q-learning,10,869,0.03400000184774399
Regular Q-learning,10,870,0.026000000536441803
Regular Q-learning,10,871,0.02800000086426735
Regular Q-learning,10,872,0.029999999329447746
Regular Q-learning,10,873,0.032999999821186066
Regular Q-learning,10,874,0.027000000700354576
Regular Q-learning,10,875,0.027000000700354576
Regular Q-learning,10,876,0.02800000086426735
Regular Q-learning,10,877,0.03500000014901161
Regular Q-learning,10,878,0.026000000536441803
Regular Q-learning,10,879,0.02800000086426735
Regular Q-learning,10,880,0.026000000536441803
Regular Q-learning,10,881,0.035999998450279236
Regular Q-learning,10,882,0.027000000700354576
Regular Q-learning,10,883,0.02800000086426735
Regular Q-learning,10,884,0.023000000044703484
Regular Q-learning,10,885,0.03799999877810478
Regular Q-learning,10,886,0.027000000700354576
Regular Q-learning,10,887,0.029999999329447746
Regular Q-learning,10,888,0.024000000208616257
Regular Q-learning,10,889,0.03400000184774399
Regular Q-learning,10,890,0.02800000086426735
Regular Q-learning,10,891,0.03099999949336052
Regular Q-learning,10,892,0.023000000044703484
Regular Q-learning,10,893,0.03400000184774399
Regular Q-learning,10,894,0.02800000086426735
Regular Q-learning,10,895,0.032999999821186066
Regular Q-learning,10,896,0.026000000536441803
Regular Q-learning,10,897,0.029999999329447746
Regular Q-learning,10,898,0.03099999949336052
Regular Q-learning,10,899,0.03200000151991844
Regular Q-learning,10,900,0.02199999988079071
Regular Q-learning,10,901,0.03200000151991844
Regular Q-learning,10,902,0.029999999329447746
Regular Q-learning,10,903,0.028999999165534973
Regular Q-learning,10,904,0.024000000208616257
Regular Q-learning,10,905,0.03200000151991844
Regular Q-learning,10,906,0.03200000151991844
Regular Q-learning,10,907,0.02800000086426735
Regular Q-learning,10,908,0.02199999988079071
Regular Q-learning,10,909,0.032999999821186066
Regular Q-learning,10,910,0.03099999949336052
Regular Q-learning,10,911,0.03099999949336052
Regular Q-learning,10,912,0.024000000208616257
Regular Q-learning,10,913,0.03099999949336052
Regular Q-learning,10,914,0.028999999165534973
Regular Q-learning,10,915,0.03099999949336052
Regular Q-learning,10,916,0.02500000037252903
Regular Q-learning,10,917,0.029999999329447746
Regular Q-learning,10,918,0.029999999329447746
Regular Q-learning,10,919,0.03099999949336052
Regular Q-learning,10,920,0.02500000037252903
Regular Q-learning,10,921,0.028999999165534973
Regular Q-learning,10,922,0.03099999949336052
Regular Q-learning,10,923,0.032999999821186066
Regular Q-learning,10,924,0.02500000037252903
Regular Q-learning,10,925,0.028999999165534973
Regular Q-learning,10,926,0.02800000086426735
Regular Q-learning,10,927,0.03099999949336052
Regular Q-learning,10,928,0.024000000208616257
Regular Q-learning,10,929,0.029999999329447746
Regular Q-learning,10,930,0.03099999949336052
Regular Q-learning,10,931,0.032999999821186066
Regular Q-learning,10,932,0.024000000208616257
Regular Q-learning,10,933,0.032999999821186066
Regular Q-learning,10,934,0.02500000037252903
Regular Q-learning,10,935,0.02500000037252903
Regular Q-learning,10,936,0.02800000086426735
Regular Q-learning,10,937,0.035999998450279236
Regular Q-learning,10,938,0.02500000037252903
Regular Q-learning,10,939,0.027000000700354576
Regular Q-learning,10,940,0.028999999165534973
Regular Q-learning,10,941,0.035999998450279236
Regular Q-learning,10,942,0.027000000700354576
Regular Q-learning,10,943,0.027000000700354576
Regular Q-learning,10,944,0.02800000086426735
Regular Q-learning,10,945,0.03500000014901161
Regular Q-learning,10,946,0.026000000536441803
Regular Q-learning,10,947,0.027000000700354576
Regular Q-learning,10,948,0.028999999165534973
Regular Q-learning,10,949,0.035999998450279236
Regular Q-learning,10,950,0.02500000037252903
Regular Q-learning,10,951,0.02800000086426735
Regular Q-learning,10,952,0.027000000700354576
Regular Q-learning,10,953,0.03400000184774399
Regular Q-learning,10,954,0.02500000037252903
Regular Q-learning,10,955,0.028999999165534973
Regular Q-learning,10,956,0.02800000086426735
Regular Q-learning,10,957,0.035999998450279236
Regular Q-learning,10,958,0.027000000700354576
Regular Q-learning,10,959,0.027000000700354576
Regular Q-learning,10,960,0.027000000700354576
Regular Q-learning,10,961,0.03400000184774399
Regular Q-learning,10,962,0.027000000700354576
Regular Q-learning,10,963,0.027000000700354576
Regular Q-learning,10,964,0.026000000536441803
Regular Q-learning,10,965,0.03400000184774399
Regular Q-learning,10,966,0.028999999165534973
Regular Q-learning,10,967,0.027000000700354576
Regular Q-learning,10,968,0.026000000536441803
Regular Q-learning,10,969,0.03400000184774399
Regular Q-learning,10,970,0.028999999165534973
Regular Q-learning,10,971,0.02800000086426735
Regular Q-learning,10,972,0.027000000700354576
Regular Q-learning,10,973,0.032999999821186066
Regular Q-learning,10,974,0.029999999329447746
Regular Q-learning,10,975,0.026000000536441803
Regular Q-learning,10,976,0.02500000037252903
Regular Q-learning,10,977,0.03400000184774399
Regular Q-learning,10,978,0.029999999329447746
Regular Q-learning,10,979,0.027000000700354576
Regular Q-learning,10,980,0.02500000037252903
Regular Q-learning,10,981,0.03400000184774399
Regular Q-learning,10,982,0.029999999329447746
Regular Q-learning,10,983,0.027000000700354576
Regular Q-learning,10,984,0.023000000044703484
Regular Q-learning,10,985,0.03400000184774399
Regular Q-learning,10,986,0.028999999165534973
Regular Q-learning,10,987,0.029999999329447746
Regular Q-learning,10,988,0.023000000044703484
Regular Q-learning,10,989,0.03500000014901161
Regular Q-learning,10,990,0.026000000536441803
Regular Q-learning,10,991,0.029999999329447746
Regular Q-learning,10,992,0.02500000037252903
Regular Q-learning,10,993,0.03500000014901161
Regular Q-learning,10,994,0.02800000086426735
Regular Q-learning,10,995,0.029999999329447746
Regular Q-learning,10,996,0.024000000208616257
Regular Q-learning,10,997,0.03400000184774399
Regular Q-learning,10,998,0.029999999329447746
Regular Q-learning,10,999,0.03099999949336052
Regular Q-learning,10,1000,0.023000000044703484
Regular Q-learning,20,1,0.27399998903274536
Regular Q-learning,20,2,0.22300000488758087
Regular Q-learning,20,3,0.16899999976158142
Regular Q-learning,20,4,0.1599999964237213
Regular Q-learning,20,5,0.14499999582767487
Regular Q-learning,20,6,0.14100000262260437
Regular Q-learning,20,7,0.13500000536441803
Regular Q-learning,20,8,0.1420000046491623
Regular Q-learning,20,9,0.13500000536441803
Regular Q-learning,20,10,0.15299999713897705
Regular Q-learning,20,11,0.13500000536441803
Regular Q-learning,20,12,0.1469999998807907
Regular Q-learning,20,13,0.11900000274181366
Regular Q-learning,20,14,0.15700000524520874
Regular Q-learning,20,15,0.12600000202655792
Regular Q-learning,20,16,0.1340000033378601
Regular Q-learning,20,17,0.10599999874830246
Regular Q-learning,20,18,0.13300000131130219
Regular Q-learning,20,19,0.11400000005960464
Regular Q-learning,20,20,0.12200000137090683
Regular Q-learning,20,21,0.11500000208616257
Regular Q-learning,20,22,0.11299999803304672
Regular Q-learning,20,23,0.10100000351667404
Regular Q-learning,20,24,0.11400000005960464
Regular Q-learning,20,25,0.10000000149011612
Regular Q-learning,20,26,0.11800000071525574
Regular Q-learning,20,27,0.1120000034570694
Regular Q-learning,20,28,0.1120000034570694
Regular Q-learning,20,29,0.09799999743700027
Regular Q-learning,20,30,0.10899999737739563
Regular Q-learning,20,31,0.10700000077486038
Regular Q-learning,20,32,0.10400000214576721
Regular Q-learning,20,33,0.10000000149011612
Regular Q-learning,20,34,0.10499999672174454
Regular Q-learning,20,35,0.09600000083446503
Regular Q-learning,20,36,0.08500000089406967
Regular Q-learning,20,37,0.09099999815225601
Regular Q-learning,20,38,0.09700000286102295
Regular Q-learning,20,39,0.08299999684095383
Regular Q-learning,20,40,0.08699999749660492
Regular Q-learning,20,41,0.0820000022649765
Regular Q-learning,20,42,0.0820000022649765
Regular Q-learning,20,43,0.08799999952316284
Regular Q-learning,20,44,0.07900000363588333
Regular Q-learning,20,45,0.08500000089406967
Regular Q-learning,20,46,0.0860000029206276
Regular Q-learning,20,47,0.08500000089406967
Regular Q-learning,20,48,0.07100000232458115
Regular Q-learning,20,49,0.07900000363588333
Regular Q-learning,20,50,0.07000000029802322
Regular Q-learning,20,51,0.07599999755620956
Regular Q-learning,20,52,0.07500000298023224
Regular Q-learning,20,53,0.07000000029802322
Regular Q-learning,20,54,0.07599999755620956
Regular Q-learning,20,55,0.07199999690055847
Regular Q-learning,20,56,0.0689999982714653
Regular Q-learning,20,57,0.07100000232458115
Regular Q-learning,20,58,0.06800000369548798
Regular Q-learning,20,59,0.06599999964237213
Regular Q-learning,20,60,0.06300000101327896
Regular Q-learning,20,61,0.07400000095367432
Regular Q-learning,20,62,0.07000000029802322
Regular Q-learning,20,63,0.06599999964237213
Regular Q-learning,20,64,0.05999999865889549
Regular Q-learning,20,65,0.07000000029802322
Regular Q-learning,20,66,0.05999999865889549
Regular Q-learning,20,67,0.06300000101327896
Regular Q-learning,20,68,0.05299999937415123
Regular Q-learning,20,69,0.0729999989271164
Regular Q-learning,20,70,0.06199999898672104
Regular Q-learning,20,71,0.06499999761581421
Regular Q-learning,20,72,0.05299999937415123
Regular Q-learning,20,73,0.06800000369548798
Regular Q-learning,20,74,0.0560000017285347
Regular Q-learning,20,75,0.061000000685453415
Regular Q-learning,20,76,0.04600000008940697
Regular Q-learning,20,77,0.0560000017285347
Regular Q-learning,20,78,0.05400000140070915
Regular Q-learning,20,79,0.06199999898672104
Regular Q-learning,20,80,0.04600000008940697
Regular Q-learning,20,81,0.057999998331069946
Regular Q-learning,20,82,0.05400000140070915
Regular Q-learning,20,83,0.06300000101327896
Regular Q-learning,20,84,0.04800000041723251
Regular Q-learning,20,85,0.061000000685453415
Regular Q-learning,20,86,0.05000000074505806
Regular Q-learning,20,87,0.05900000035762787
Regular Q-learning,20,88,0.050999999046325684
Regular Q-learning,20,89,0.05700000002980232
Regular Q-learning,20,90,0.04899999871850014
Regular Q-learning,20,91,0.05999999865889549
Regular Q-learning,20,92,0.052000001072883606
Regular Q-learning,20,93,0.05400000140070915
Regular Q-learning,20,94,0.04699999839067459
Regular Q-learning,20,95,0.05900000035762787
Regular Q-learning,20,96,0.04600000008940697
Regular Q-learning,20,97,0.05400000140070915
Regular Q-learning,20,98,0.04800000041723251
Regular Q-learning,20,99,0.057999998331069946
Regular Q-learning,20,100,0.04699999839067459
Regular Q-learning,20,101,0.0560000017285347
Regular Q-learning,20,102,0.04800000041723251
Regular Q-learning,20,103,0.05700000002980232
Regular Q-learning,20,104,0.04500000178813934
Regular Q-learning,20,105,0.050999999046325684
Regular Q-learning,20,106,0.052000001072883606
Regular Q-learning,20,107,0.054999999701976776
Regular Q-learning,20,108,0.0430000014603138
Regular Q-learning,20,109,0.05900000035762787
Regular Q-learning,20,110,0.04800000041723251
Regular Q-learning,20,111,0.057999998331069946
Regular Q-learning,20,112,0.04800000041723251
Regular Q-learning,20,113,0.05700000002980232
Regular Q-learning,20,114,0.04600000008940697
Regular Q-learning,20,115,0.05900000035762787
Regular Q-learning,20,116,0.04500000178813934
Regular Q-learning,20,117,0.05400000140070915
Regular Q-learning,20,118,0.04699999839067459
Regular Q-learning,20,119,0.06199999898672104
Regular Q-learning,20,120,0.0430000014603138
Regular Q-learning,20,121,0.0560000017285347
Regular Q-learning,20,122,0.0430000014603138
Regular Q-learning,20,123,0.057999998331069946
Regular Q-learning,20,124,0.04600000008940697
Regular Q-learning,20,125,0.04800000041723251
Regular Q-learning,20,126,0.04399999976158142
Regular Q-learning,20,127,0.0560000017285347
Regular Q-learning,20,128,0.04100000113248825
Regular Q-learning,20,129,0.057999998331069946
Regular Q-learning,20,130,0.0430000014603138
Regular Q-learning,20,131,0.057999998331069946
Regular Q-learning,20,132,0.04500000178813934
Regular Q-learning,20,133,0.05900000035762787
Regular Q-learning,20,134,0.04899999871850014
Regular Q-learning,20,135,0.05000000074505806
Regular Q-learning,20,136,0.04500000178813934
Regular Q-learning,20,137,0.05999999865889549
Regular Q-learning,20,138,0.04500000178813934
Regular Q-learning,20,139,0.050999999046325684
Regular Q-learning,20,140,0.041999999433755875
Regular Q-learning,20,141,0.05900000035762787
Regular Q-learning,20,142,0.04600000008940697
Regular Q-learning,20,143,0.05299999937415123
Regular Q-learning,20,144,0.041999999433755875
Regular Q-learning,20,145,0.057999998331069946
Regular Q-learning,20,146,0.04699999839067459
Regular Q-learning,20,147,0.05400000140070915
Regular Q-learning,20,148,0.03999999910593033
Regular Q-learning,20,149,0.05400000140070915
Regular Q-learning,20,150,0.04600000008940697
Regular Q-learning,20,151,0.052000001072883606
Regular Q-learning,20,152,0.0430000014603138
Regular Q-learning,20,153,0.05400000140070915
Regular Q-learning,20,154,0.04399999976158142
Regular Q-learning,20,155,0.054999999701976776
Regular Q-learning,20,156,0.039000000804662704
Regular Q-learning,20,157,0.050999999046325684
Regular Q-learning,20,158,0.04800000041723251
Regular Q-learning,20,159,0.050999999046325684
Regular Q-learning,20,160,0.039000000804662704
Regular Q-learning,20,161,0.052000001072883606
Regular Q-learning,20,162,0.04500000178813934
Regular Q-learning,20,163,0.052000001072883606
Regular Q-learning,20,164,0.039000000804662704
Regular Q-learning,20,165,0.052000001072883606
Regular Q-learning,20,166,0.0430000014603138
Regular Q-learning,20,167,0.052000001072883606
Regular Q-learning,20,168,0.03799999877810478
Regular Q-learning,20,169,0.052000001072883606
Regular Q-learning,20,170,0.041999999433755875
Regular Q-learning,20,171,0.050999999046325684
Regular Q-learning,20,172,0.041999999433755875
Regular Q-learning,20,173,0.052000001072883606
Regular Q-learning,20,174,0.03999999910593033
Regular Q-learning,20,175,0.05000000074505806
Regular Q-learning,20,176,0.04399999976158142
Regular Q-learning,20,177,0.050999999046325684
Regular Q-learning,20,178,0.03799999877810478
Regular Q-learning,20,179,0.04800000041723251
Regular Q-learning,20,180,0.0430000014603138
Regular Q-learning,20,181,0.04800000041723251
Regular Q-learning,20,182,0.04100000113248825
Regular Q-learning,20,183,0.05000000074505806
Regular Q-learning,20,184,0.04100000113248825
Regular Q-learning,20,185,0.04800000041723251
Regular Q-learning,20,186,0.04399999976158142
Regular Q-learning,20,187,0.04800000041723251
Regular Q-learning,20,188,0.04100000113248825
Regular Q-learning,20,189,0.04800000041723251
Regular Q-learning,20,190,0.04600000008940697
Regular Q-learning,20,191,0.05000000074505806
Regular Q-learning,20,192,0.04399999976158142
Regular Q-learning,20,193,0.05000000074505806
Regular Q-learning,20,194,0.0430000014603138
Regular Q-learning,20,195,0.04800000041723251
Regular Q-learning,20,196,0.04699999839067459
Regular Q-learning,20,197,0.05000000074505806
Regular Q-learning,20,198,0.04100000113248825
Regular Q-learning,20,199,0.04699999839067459
Regular Q-learning,20,200,0.04500000178813934
Regular Q-learning,20,201,0.04399999976158142
Regular Q-learning,20,202,0.039000000804662704
Regular Q-learning,20,203,0.050999999046325684
Regular Q-learning,20,204,0.04500000178813934
Regular Q-learning,20,205,0.05000000074505806
Regular Q-learning,20,206,0.03999999910593033
Regular Q-learning,20,207,0.04899999871850014
Regular Q-learning,20,208,0.05000000074505806
Regular Q-learning,20,209,0.04800000041723251
Regular Q-learning,20,210,0.039000000804662704
Regular Q-learning,20,211,0.05000000074505806
Regular Q-learning,20,212,0.04699999839067459
Regular Q-learning,20,213,0.041999999433755875
Regular Q-learning,20,214,0.03400000184774399
Regular Q-learning,20,215,0.052000001072883606
Regular Q-learning,20,216,0.03999999910593033
Regular Q-learning,20,217,0.04600000008940697
Regular Q-learning,20,218,0.03799999877810478
Regular Q-learning,20,219,0.05000000074505806
Regular Q-learning,20,220,0.04500000178813934
Regular Q-learning,20,221,0.04399999976158142
Regular Q-learning,20,222,0.0430000014603138
Regular Q-learning,20,223,0.05400000140070915
Regular Q-learning,20,224,0.04600000008940697
Regular Q-learning,20,225,0.0430000014603138
Regular Q-learning,20,226,0.041999999433755875
Regular Q-learning,20,227,0.05000000074505806
Regular Q-learning,20,228,0.04600000008940697
Regular Q-learning,20,229,0.04500000178813934
Regular Q-learning,20,230,0.03700000047683716
Regular Q-learning,20,231,0.052000001072883606
Regular Q-learning,20,232,0.0430000014603138
Regular Q-learning,20,233,0.04399999976158142
Regular Q-learning,20,234,0.03700000047683716
Regular Q-learning,20,235,0.04899999871850014
Regular Q-learning,20,236,0.04899999871850014
Regular Q-learning,20,237,0.039000000804662704
Regular Q-learning,20,238,0.039000000804662704
Regular Q-learning,20,239,0.04899999871850014
Regular Q-learning,20,240,0.0430000014603138
Regular Q-learning,20,241,0.04699999839067459
Regular Q-learning,20,242,0.04399999976158142
Regular Q-learning,20,243,0.050999999046325684
Regular Q-learning,20,244,0.04699999839067459
Regular Q-learning,20,245,0.04100000113248825
Regular Q-learning,20,246,0.04500000178813934
Regular Q-learning,20,247,0.05000000074505806
Regular Q-learning,20,248,0.041999999433755875
Regular Q-learning,20,249,0.04500000178813934
Regular Q-learning,20,250,0.04500000178813934
Regular Q-learning,20,251,0.054999999701976776
Regular Q-learning,20,252,0.04500000178813934
Regular Q-learning,20,253,0.03799999877810478
Regular Q-learning,20,254,0.04399999976158142
Regular Q-learning,20,255,0.05000000074505806
Regular Q-learning,20,256,0.04399999976158142
Regular Q-learning,20,257,0.04699999839067459
Regular Q-learning,20,258,0.04399999976158142
Regular Q-learning,20,259,0.04600000008940697
Regular Q-learning,20,260,0.04399999976158142
Regular Q-learning,20,261,0.041999999433755875
Regular Q-learning,20,262,0.04500000178813934
Regular Q-learning,20,263,0.052000001072883606
Regular Q-learning,20,264,0.04100000113248825
Regular Q-learning,20,265,0.04399999976158142
Regular Q-learning,20,266,0.0430000014603138
Regular Q-learning,20,267,0.05400000140070915
Regular Q-learning,20,268,0.0430000014603138
Regular Q-learning,20,269,0.04500000178813934
Regular Q-learning,20,270,0.04500000178813934
Regular Q-learning,20,271,0.050999999046325684
Regular Q-learning,20,272,0.041999999433755875
Regular Q-learning,20,273,0.04399999976158142
Regular Q-learning,20,274,0.04100000113248825
Regular Q-learning,20,275,0.052000001072883606
Regular Q-learning,20,276,0.039000000804662704
Regular Q-learning,20,277,0.041999999433755875
Regular Q-learning,20,278,0.0430000014603138
Regular Q-learning,20,279,0.05000000074505806
Regular Q-learning,20,280,0.04500000178813934
Regular Q-learning,20,281,0.0430000014603138
Regular Q-learning,20,282,0.04100000113248825
Regular Q-learning,20,283,0.05299999937415123
Regular Q-learning,20,284,0.04399999976158142
Regular Q-learning,20,285,0.041999999433755875
Regular Q-learning,20,286,0.04500000178813934
Regular Q-learning,20,287,0.050999999046325684
Regular Q-learning,20,288,0.0430000014603138
Regular Q-learning,20,289,0.041999999433755875
Regular Q-learning,20,290,0.04100000113248825
Regular Q-learning,20,291,0.04899999871850014
Regular Q-learning,20,292,0.04500000178813934
Regular Q-learning,20,293,0.039000000804662704
Regular Q-learning,20,294,0.04600000008940697
Regular Q-learning,20,295,0.04899999871850014
Regular Q-learning,20,296,0.03999999910593033
Regular Q-learning,20,297,0.04600000008940697
Regular Q-learning,20,298,0.04100000113248825
Regular Q-learning,20,299,0.052000001072883606
Regular Q-learning,20,300,0.03700000047683716
Regular Q-learning,20,301,0.03999999910593033
Regular Q-learning,20,302,0.041999999433755875
Regular Q-learning,20,303,0.052000001072883606
Regular Q-learning,20,304,0.04600000008940697
Regular Q-learning,20,305,0.04100000113248825
Regular Q-learning,20,306,0.041999999433755875
Regular Q-learning,20,307,0.05000000074505806
Regular Q-learning,20,308,0.04399999976158142
Regular Q-learning,20,309,0.0430000014603138
Regular Q-learning,20,310,0.04100000113248825
Regular Q-learning,20,311,0.052000001072883606
Regular Q-learning,20,312,0.03799999877810478
Regular Q-learning,20,313,0.04600000008940697
Regular Q-learning,20,314,0.04500000178813934
Regular Q-learning,20,315,0.04899999871850014
Regular Q-learning,20,316,0.0430000014603138
Regular Q-learning,20,317,0.0430000014603138
Regular Q-learning,20,318,0.04699999839067459
Regular Q-learning,20,319,0.04899999871850014
Regular Q-learning,20,320,0.03400000184774399
Regular Q-learning,20,321,0.04600000008940697
Regular Q-learning,20,322,0.04800000041723251
Regular Q-learning,20,323,0.04399999976158142
Regular Q-learning,20,324,0.039000000804662704
Regular Q-learning,20,325,0.04399999976158142
Regular Q-learning,20,326,0.04899999871850014
Regular Q-learning,20,327,0.04899999871850014
Regular Q-learning,20,328,0.04100000113248825
Regular Q-learning,20,329,0.0430000014603138
Regular Q-learning,20,330,0.04699999839067459
Regular Q-learning,20,331,0.04600000008940697
Regular Q-learning,20,332,0.03700000047683716
Regular Q-learning,20,333,0.04399999976158142
Regular Q-learning,20,334,0.04399999976158142
Regular Q-learning,20,335,0.04899999871850014
Regular Q-learning,20,336,0.04100000113248825
Regular Q-learning,20,337,0.04100000113248825
Regular Q-learning,20,338,0.0430000014603138
Regular Q-learning,20,339,0.04899999871850014
Regular Q-learning,20,340,0.0430000014603138
Regular Q-learning,20,341,0.041999999433755875
Regular Q-learning,20,342,0.04100000113248825
Regular Q-learning,20,343,0.04800000041723251
Regular Q-learning,20,344,0.04399999976158142
Regular Q-learning,20,345,0.04100000113248825
Regular Q-learning,20,346,0.041999999433755875
Regular Q-learning,20,347,0.04500000178813934
Regular Q-learning,20,348,0.04399999976158142
Regular Q-learning,20,349,0.03999999910593033
Regular Q-learning,20,350,0.039000000804662704
Regular Q-learning,20,351,0.05400000140070915
Regular Q-learning,20,352,0.0430000014603138
Regular Q-learning,20,353,0.039000000804662704
Regular Q-learning,20,354,0.03799999877810478
Regular Q-learning,20,355,0.04899999871850014
Regular Q-learning,20,356,0.04500000178813934
Regular Q-learning,20,357,0.041999999433755875
Regular Q-learning,20,358,0.03799999877810478
Regular Q-learning,20,359,0.04800000041723251
Regular Q-learning,20,360,0.0430000014603138
Regular Q-learning,20,361,0.04399999976158142
Regular Q-learning,20,362,0.03799999877810478
Regular Q-learning,20,363,0.050999999046325684
Regular Q-learning,20,364,0.04500000178813934
Regular Q-learning,20,365,0.0430000014603138
Regular Q-learning,20,366,0.03799999877810478
Regular Q-learning,20,367,0.04399999976158142
Regular Q-learning,20,368,0.04600000008940697
Regular Q-learning,20,369,0.041999999433755875
Regular Q-learning,20,370,0.035999998450279236
Regular Q-learning,20,371,0.04800000041723251
Regular Q-learning,20,372,0.04699999839067459
Regular Q-learning,20,373,0.0430000014603138
Regular Q-learning,20,374,0.039000000804662704
Regular Q-learning,20,375,0.05000000074505806
Regular Q-learning,20,376,0.04699999839067459
Regular Q-learning,20,377,0.041999999433755875
Regular Q-learning,20,378,0.03500000014901161
Regular Q-learning,20,379,0.052000001072883606
Regular Q-learning,20,380,0.041999999433755875
Regular Q-learning,20,381,0.039000000804662704
Regular Q-learning,20,382,0.03999999910593033
Regular Q-learning,20,383,0.05000000074505806
Regular Q-learning,20,384,0.03999999910593033
Regular Q-learning,20,385,0.0430000014603138
Regular Q-learning,20,386,0.039000000804662704
Regular Q-learning,20,387,0.04699999839067459
Regular Q-learning,20,388,0.0430000014603138
Regular Q-learning,20,389,0.04500000178813934
Regular Q-learning,20,390,0.03500000014901161
Regular Q-learning,20,391,0.04899999871850014
Regular Q-learning,20,392,0.0430000014603138
Regular Q-learning,20,393,0.04899999871850014
Regular Q-learning,20,394,0.03799999877810478
Regular Q-learning,20,395,0.04399999976158142
Regular Q-learning,20,396,0.03999999910593033
Regular Q-learning,20,397,0.04500000178813934
Regular Q-learning,20,398,0.039000000804662704
Regular Q-learning,20,399,0.04500000178813934
Regular Q-learning,20,400,0.041999999433755875
Regular Q-learning,20,401,0.04899999871850014
Regular Q-learning,20,402,0.035999998450279236
Regular Q-learning,20,403,0.04100000113248825
Regular Q-learning,20,404,0.04399999976158142
Regular Q-learning,20,405,0.04800000041723251
Regular Q-learning,20,406,0.035999998450279236
Regular Q-learning,20,407,0.04600000008940697
Regular Q-learning,20,408,0.04500000178813934
Regular Q-learning,20,409,0.0430000014603138
Regular Q-learning,20,410,0.039000000804662704
Regular Q-learning,20,411,0.04500000178813934
Regular Q-learning,20,412,0.03799999877810478
Regular Q-learning,20,413,0.04800000041723251
Regular Q-learning,20,414,0.035999998450279236
Regular Q-learning,20,415,0.04500000178813934
Regular Q-learning,20,416,0.04500000178813934
Regular Q-learning,20,417,0.04500000178813934
Regular Q-learning,20,418,0.035999998450279236
Regular Q-learning,20,419,0.04500000178813934
Regular Q-learning,20,420,0.03999999910593033
Regular Q-learning,20,421,0.04800000041723251
Regular Q-learning,20,422,0.03799999877810478
Regular Q-learning,20,423,0.05000000074505806
Regular Q-learning,20,424,0.03799999877810478
Regular Q-learning,20,425,0.04399999976158142
Regular Q-learning,20,426,0.039000000804662704
Regular Q-learning,20,427,0.04600000008940697
Regular Q-learning,20,428,0.035999998450279236
Regular Q-learning,20,429,0.04500000178813934
Regular Q-learning,20,430,0.03999999910593033
Regular Q-learning,20,431,0.04600000008940697
Regular Q-learning,20,432,0.03799999877810478
Regular Q-learning,20,433,0.04899999871850014
Regular Q-learning,20,434,0.035999998450279236
Regular Q-learning,20,435,0.04500000178813934
Regular Q-learning,20,436,0.039000000804662704
Regular Q-learning,20,437,0.04500000178813934
Regular Q-learning,20,438,0.03400000184774399
Regular Q-learning,20,439,0.04899999871850014
Regular Q-learning,20,440,0.03999999910593033
Regular Q-learning,20,441,0.041999999433755875
Regular Q-learning,20,442,0.03400000184774399
Regular Q-learning,20,443,0.05000000074505806
Regular Q-learning,20,444,0.03799999877810478
Regular Q-learning,20,445,0.0430000014603138
Regular Q-learning,20,446,0.03400000184774399
Regular Q-learning,20,447,0.04800000041723251
Regular Q-learning,20,448,0.03999999910593033
Regular Q-learning,20,449,0.04399999976158142
Regular Q-learning,20,450,0.03999999910593033
Regular Q-learning,20,451,0.04600000008940697
Regular Q-learning,20,452,0.035999998450279236
Regular Q-learning,20,453,0.04500000178813934
Regular Q-learning,20,454,0.039000000804662704
Regular Q-learning,20,455,0.0430000014603138
Regular Q-learning,20,456,0.03400000184774399
Regular Q-learning,20,457,0.04500000178813934
Regular Q-learning,20,458,0.03999999910593033
Regular Q-learning,20,459,0.04500000178813934
Regular Q-learning,20,460,0.03500000014901161
Regular Q-learning,20,461,0.0430000014603138
Regular Q-learning,20,462,0.039000000804662704
Regular Q-learning,20,463,0.04500000178813934
Regular Q-learning,20,464,0.03400000184774399
Regular Q-learning,20,465,0.04500000178813934
Regular Q-learning,20,466,0.03799999877810478
Regular Q-learning,20,467,0.04399999976158142
Regular Q-learning,20,468,0.03200000151991844
Regular Q-learning,20,469,0.0430000014603138
Regular Q-learning,20,470,0.03999999910593033
Regular Q-learning,20,471,0.04600000008940697
Regular Q-learning,20,472,0.03700000047683716
Regular Q-learning,20,473,0.04699999839067459
Regular Q-learning,20,474,0.04100000113248825
Regular Q-learning,20,475,0.041999999433755875
Regular Q-learning,20,476,0.032999999821186066
Regular Q-learning,20,477,0.04800000041723251
Regular Q-learning,20,478,0.041999999433755875
Regular Q-learning,20,479,0.04399999976158142
Regular Q-learning,20,480,0.035999998450279236
Regular Q-learning,20,481,0.04600000008940697
Regular Q-learning,20,482,0.03500000014901161
Regular Q-learning,20,483,0.04500000178813934
Regular Q-learning,20,484,0.032999999821186066
Regular Q-learning,20,485,0.0430000014603138
Regular Q-learning,20,486,0.03700000047683716
Regular Q-learning,20,487,0.04800000041723251
Regular Q-learning,20,488,0.03099999949336052
Regular Q-learning,20,489,0.04899999871850014
Regular Q-learning,20,490,0.03500000014901161
Regular Q-learning,20,491,0.04399999976158142
Regular Q-learning,20,492,0.03099999949336052
Regular Q-learning,20,493,0.050999999046325684
Regular Q-learning,20,494,0.03700000047683716
Regular Q-learning,20,495,0.04100000113248825
Regular Q-learning,20,496,0.029999999329447746
Regular Q-learning,20,497,0.05000000074505806
Regular Q-learning,20,498,0.03500000014901161
Regular Q-learning,20,499,0.04399999976158142
Regular Q-learning,20,500,0.029999999329447746
Regular Q-learning,20,501,0.04800000041723251
Regular Q-learning,20,502,0.03400000184774399
Regular Q-learning,20,503,0.0430000014603138
Regular Q-learning,20,504,0.03200000151991844
Regular Q-learning,20,505,0.04699999839067459
Regular Q-learning,20,506,0.035999998450279236
Regular Q-learning,20,507,0.04399999976158142
Regular Q-learning,20,508,0.03099999949336052
Regular Q-learning,20,509,0.04699999839067459
Regular Q-learning,20,510,0.03400000184774399
Regular Q-learning,20,511,0.0430000014603138
Regular Q-learning,20,512,0.03400000184774399
Regular Q-learning,20,513,0.04500000178813934
Regular Q-learning,20,514,0.03400000184774399
Regular Q-learning,20,515,0.0430000014603138
Regular Q-learning,20,516,0.03099999949336052
Regular Q-learning,20,517,0.04800000041723251
Regular Q-learning,20,518,0.03500000014901161
Regular Q-learning,20,519,0.0430000014603138
Regular Q-learning,20,520,0.03099999949336052
Regular Q-learning,20,521,0.050999999046325684
Regular Q-learning,20,522,0.03500000014901161
Regular Q-learning,20,523,0.04600000008940697
Regular Q-learning,20,524,0.029999999329447746
Regular Q-learning,20,525,0.05000000074505806
Regular Q-learning,20,526,0.03400000184774399
Regular Q-learning,20,527,0.04600000008940697
Regular Q-learning,20,528,0.032999999821186066
Regular Q-learning,20,529,0.04600000008940697
Regular Q-learning,20,530,0.028999999165534973
Regular Q-learning,20,531,0.04600000008940697
Regular Q-learning,20,532,0.03099999949336052
Regular Q-learning,20,533,0.04699999839067459
Regular Q-learning,20,534,0.03200000151991844
Regular Q-learning,20,535,0.04800000041723251
Regular Q-learning,20,536,0.03200000151991844
Regular Q-learning,20,537,0.04500000178813934
Regular Q-learning,20,538,0.03099999949336052
Regular Q-learning,20,539,0.04699999839067459
Regular Q-learning,20,540,0.029999999329447746
Regular Q-learning,20,541,0.04800000041723251
Regular Q-learning,20,542,0.03099999949336052
Regular Q-learning,20,543,0.04500000178813934
Regular Q-learning,20,544,0.032999999821186066
Regular Q-learning,20,545,0.04699999839067459
Regular Q-learning,20,546,0.03099999949336052
Regular Q-learning,20,547,0.04100000113248825
Regular Q-learning,20,548,0.032999999821186066
Regular Q-learning,20,549,0.04699999839067459
Regular Q-learning,20,550,0.029999999329447746
Regular Q-learning,20,551,0.04399999976158142
Regular Q-learning,20,552,0.029999999329447746
Regular Q-learning,20,553,0.04699999839067459
Regular Q-learning,20,554,0.03400000184774399
Regular Q-learning,20,555,0.04399999976158142
Regular Q-learning,20,556,0.03099999949336052
Regular Q-learning,20,557,0.04600000008940697
Regular Q-learning,20,558,0.032999999821186066
Regular Q-learning,20,559,0.0430000014603138
Regular Q-learning,20,560,0.03200000151991844
Regular Q-learning,20,561,0.04399999976158142
Regular Q-learning,20,562,0.03400000184774399
Regular Q-learning,20,563,0.0430000014603138
Regular Q-learning,20,564,0.029999999329447746
Regular Q-learning,20,565,0.04500000178813934
Regular Q-learning,20,566,0.03400000184774399
Regular Q-learning,20,567,0.041999999433755875
Regular Q-learning,20,568,0.03400000184774399
Regular Q-learning,20,569,0.03999999910593033
Regular Q-learning,20,570,0.03700000047683716
Regular Q-learning,20,571,0.03999999910593033
Regular Q-learning,20,572,0.032999999821186066
Regular Q-learning,20,573,0.04100000113248825
Regular Q-learning,20,574,0.035999998450279236
Regular Q-learning,20,575,0.041999999433755875
Regular Q-learning,20,576,0.03200000151991844
Regular Q-learning,20,577,0.041999999433755875
Regular Q-learning,20,578,0.035999998450279236
Regular Q-learning,20,579,0.04399999976158142
Regular Q-learning,20,580,0.032999999821186066
Regular Q-learning,20,581,0.041999999433755875
Regular Q-learning,20,582,0.03500000014901161
Regular Q-learning,20,583,0.041999999433755875
Regular Q-learning,20,584,0.03099999949336052
Regular Q-learning,20,585,0.0430000014603138
Regular Q-learning,20,586,0.035999998450279236
Regular Q-learning,20,587,0.041999999433755875
Regular Q-learning,20,588,0.029999999329447746
Regular Q-learning,20,589,0.04100000113248825
Regular Q-learning,20,590,0.03700000047683716
Regular Q-learning,20,591,0.04399999976158142
Regular Q-learning,20,592,0.03099999949336052
Regular Q-learning,20,593,0.0430000014603138
Regular Q-learning,20,594,0.035999998450279236
Regular Q-learning,20,595,0.041999999433755875
Regular Q-learning,20,596,0.03200000151991844
Regular Q-learning,20,597,0.0430000014603138
Regular Q-learning,20,598,0.035999998450279236
Regular Q-learning,20,599,0.039000000804662704
Regular Q-learning,20,600,0.035999998450279236
Regular Q-learning,20,601,0.041999999433755875
Regular Q-learning,20,602,0.03400000184774399
Regular Q-learning,20,603,0.039000000804662704
Regular Q-learning,20,604,0.03400000184774399
Regular Q-learning,20,605,0.041999999433755875
Regular Q-learning,20,606,0.03500000014901161
Regular Q-learning,20,607,0.03999999910593033
Regular Q-learning,20,608,0.03400000184774399
Regular Q-learning,20,609,0.041999999433755875
Regular Q-learning,20,610,0.03700000047683716
Regular Q-learning,20,611,0.03999999910593033
Regular Q-learning,20,612,0.032999999821186066
Regular Q-learning,20,613,0.041999999433755875
Regular Q-learning,20,614,0.032999999821186066
Regular Q-learning,20,615,0.04100000113248825
Regular Q-learning,20,616,0.03400000184774399
Regular Q-learning,20,617,0.039000000804662704
Regular Q-learning,20,618,0.03999999910593033
Regular Q-learning,20,619,0.039000000804662704
Regular Q-learning,20,620,0.03200000151991844
Regular Q-learning,20,621,0.041999999433755875
Regular Q-learning,20,622,0.03799999877810478
Regular Q-learning,20,623,0.039000000804662704
Regular Q-learning,20,624,0.032999999821186066
Regular Q-learning,20,625,0.04100000113248825
Regular Q-learning,20,626,0.039000000804662704
Regular Q-learning,20,627,0.039000000804662704
Regular Q-learning,20,628,0.03200000151991844
Regular Q-learning,20,629,0.0430000014603138
Regular Q-learning,20,630,0.03700000047683716
Regular Q-learning,20,631,0.04100000113248825
Regular Q-learning,20,632,0.03099999949336052
Regular Q-learning,20,633,0.0430000014603138
Regular Q-learning,20,634,0.03799999877810478
Regular Q-learning,20,635,0.04100000113248825
Regular Q-learning,20,636,0.02800000086426735
Regular Q-learning,20,637,0.04100000113248825
Regular Q-learning,20,638,0.03799999877810478
Regular Q-learning,20,639,0.04100000113248825
Regular Q-learning,20,640,0.028999999165534973
Regular Q-learning,20,641,0.041999999433755875
Regular Q-learning,20,642,0.039000000804662704
Regular Q-learning,20,643,0.04100000113248825
Regular Q-learning,20,644,0.02800000086426735
Regular Q-learning,20,645,0.04100000113248825
Regular Q-learning,20,646,0.03999999910593033
Regular Q-learning,20,647,0.04100000113248825
Regular Q-learning,20,648,0.028999999165534973
Regular Q-learning,20,649,0.039000000804662704
Regular Q-learning,20,650,0.03999999910593033
Regular Q-learning,20,651,0.04399999976158142
Regular Q-learning,20,652,0.029999999329447746
Regular Q-learning,20,653,0.03799999877810478
Regular Q-learning,20,654,0.039000000804662704
Regular Q-learning,20,655,0.0430000014603138
Regular Q-learning,20,656,0.028999999165534973
Regular Q-learning,20,657,0.039000000804662704
Regular Q-learning,20,658,0.03999999910593033
Regular Q-learning,20,659,0.0430000014603138
Regular Q-learning,20,660,0.029999999329447746
Regular Q-learning,20,661,0.03999999910593033
Regular Q-learning,20,662,0.039000000804662704
Regular Q-learning,20,663,0.0430000014603138
Regular Q-learning,20,664,0.028999999165534973
Regular Q-learning,20,665,0.039000000804662704
Regular Q-learning,20,666,0.03799999877810478
Regular Q-learning,20,667,0.04399999976158142
Regular Q-learning,20,668,0.02800000086426735
Regular Q-learning,20,669,0.03799999877810478
Regular Q-learning,20,670,0.039000000804662704
Regular Q-learning,20,671,0.04399999976158142
Regular Q-learning,20,672,0.028999999165534973
Regular Q-learning,20,673,0.03999999910593033
Regular Q-learning,20,674,0.035999998450279236
Regular Q-learning,20,675,0.041999999433755875
Regular Q-learning,20,676,0.029999999329447746
Regular Q-learning,20,677,0.0430000014603138
Regular Q-learning,20,678,0.03799999877810478
Regular Q-learning,20,679,0.0430000014603138
Regular Q-learning,20,680,0.02800000086426735
Regular Q-learning,20,681,0.04399999976158142
Regular Q-learning,20,682,0.03799999877810478
Regular Q-learning,20,683,0.041999999433755875
Regular Q-learning,20,684,0.027000000700354576
Regular Q-learning,20,685,0.041999999433755875
Regular Q-learning,20,686,0.039000000804662704
Regular Q-learning,20,687,0.041999999433755875
Regular Q-learning,20,688,0.028999999165534973
Regular Q-learning,20,689,0.04100000113248825
Regular Q-learning,20,690,0.039000000804662704
Regular Q-learning,20,691,0.041999999433755875
Regular Q-learning,20,692,0.029999999329447746
Regular Q-learning,20,693,0.04100000113248825
Regular Q-learning,20,694,0.03799999877810478
Regular Q-learning,20,695,0.04600000008940697
Regular Q-learning,20,696,0.02800000086426735
Regular Q-learning,20,697,0.04100000113248825
Regular Q-learning,20,698,0.04100000113248825
Regular Q-learning,20,699,0.03999999910593033
Regular Q-learning,20,700,0.02800000086426735
Regular Q-learning,20,701,0.0430000014603138
Regular Q-learning,20,702,0.03700000047683716
Regular Q-learning,20,703,0.041999999433755875
Regular Q-learning,20,704,0.028999999165534973
Regular Q-learning,20,705,0.03799999877810478
Regular Q-learning,20,706,0.039000000804662704
Regular Q-learning,20,707,0.04100000113248825
Regular Q-learning,20,708,0.02800000086426735
Regular Q-learning,20,709,0.04100000113248825
Regular Q-learning,20,710,0.03799999877810478
Regular Q-learning,20,711,0.03999999910593033
Regular Q-learning,20,712,0.02800000086426735
Regular Q-learning,20,713,0.03799999877810478
Regular Q-learning,20,714,0.03999999910593033
Regular Q-learning,20,715,0.041999999433755875
Regular Q-learning,20,716,0.03099999949336052
Regular Q-learning,20,717,0.0430000014603138
Regular Q-learning,20,718,0.03799999877810478
Regular Q-learning,20,719,0.039000000804662704
Regular Q-learning,20,720,0.03099999949336052
Regular Q-learning,20,721,0.041999999433755875
Regular Q-learning,20,722,0.03700000047683716
Regular Q-learning,20,723,0.04100000113248825
Regular Q-learning,20,724,0.029999999329447746
Regular Q-learning,20,725,0.04100000113248825
Regular Q-learning,20,726,0.03700000047683716
Regular Q-learning,20,727,0.04100000113248825
Regular Q-learning,20,728,0.03200000151991844
Regular Q-learning,20,729,0.03999999910593033
Regular Q-learning,20,730,0.035999998450279236
Regular Q-learning,20,731,0.03999999910593033
Regular Q-learning,20,732,0.028999999165534973
Regular Q-learning,20,733,0.04399999976158142
Regular Q-learning,20,734,0.035999998450279236
Regular Q-learning,20,735,0.03700000047683716
Regular Q-learning,20,736,0.03099999949336052
Regular Q-learning,20,737,0.0430000014603138
Regular Q-learning,20,738,0.035999998450279236
Regular Q-learning,20,739,0.03799999877810478
Regular Q-learning,20,740,0.03200000151991844
Regular Q-learning,20,741,0.041999999433755875
Regular Q-learning,20,742,0.03500000014901161
Regular Q-learning,20,743,0.039000000804662704
Regular Q-learning,20,744,0.03200000151991844
Regular Q-learning,20,745,0.0430000014603138
Regular Q-learning,20,746,0.03400000184774399
Regular Q-learning,20,747,0.03799999877810478
Regular Q-learning,20,748,0.03200000151991844
Regular Q-learning,20,749,0.0430000014603138
Regular Q-learning,20,750,0.03500000014901161
Regular Q-learning,20,751,0.035999998450279236
Regular Q-learning,20,752,0.032999999821186066
Regular Q-learning,20,753,0.04399999976158142
Regular Q-learning,20,754,0.03500000014901161
Regular Q-learning,20,755,0.039000000804662704
Regular Q-learning,20,756,0.03200000151991844
Regular Q-learning,20,757,0.0430000014603138
Regular Q-learning,20,758,0.032999999821186066
Regular Q-learning,20,759,0.03700000047683716
Regular Q-learning,20,760,0.029999999329447746
Regular Q-learning,20,761,0.041999999433755875
Regular Q-learning,20,762,0.03400000184774399
Regular Q-learning,20,763,0.03999999910593033
Regular Q-learning,20,764,0.028999999165534973
Regular Q-learning,20,765,0.04100000113248825
Regular Q-learning,20,766,0.03700000047683716
Regular Q-learning,20,767,0.03999999910593033
Regular Q-learning,20,768,0.028999999165534973
Regular Q-learning,20,769,0.04800000041723251
Regular Q-learning,20,770,0.03500000014901161
Regular Q-learning,20,771,0.03700000047683716
Regular Q-learning,20,772,0.027000000700354576
Regular Q-learning,20,773,0.0430000014603138
Regular Q-learning,20,774,0.03799999877810478
Regular Q-learning,20,775,0.03500000014901161
Regular Q-learning,20,776,0.028999999165534973
Regular Q-learning,20,777,0.04500000178813934
Regular Q-learning,20,778,0.032999999821186066
Regular Q-learning,20,779,0.03700000047683716
Regular Q-learning,20,780,0.02800000086426735
Regular Q-learning,20,781,0.041999999433755875
Regular Q-learning,20,782,0.03200000151991844
Regular Q-learning,20,783,0.03799999877810478
Regular Q-learning,20,784,0.03400000184774399
Regular Q-learning,20,785,0.041999999433755875
Regular Q-learning,20,786,0.03700000047683716
Regular Q-learning,20,787,0.03700000047683716
Regular Q-learning,20,788,0.03400000184774399
Regular Q-learning,20,789,0.041999999433755875
Regular Q-learning,20,790,0.035999998450279236
Regular Q-learning,20,791,0.03400000184774399
Regular Q-learning,20,792,0.03400000184774399
Regular Q-learning,20,793,0.04100000113248825
Regular Q-learning,20,794,0.035999998450279236
Regular Q-learning,20,795,0.03799999877810478
Regular Q-learning,20,796,0.029999999329447746
Regular Q-learning,20,797,0.04100000113248825
Regular Q-learning,20,798,0.03799999877810478
Regular Q-learning,20,799,0.035999998450279236
Regular Q-learning,20,800,0.029999999329447746
Regular Q-learning,20,801,0.041999999433755875
Regular Q-learning,20,802,0.03700000047683716
Regular Q-learning,20,803,0.03999999910593033
Regular Q-learning,20,804,0.028999999165534973
Regular Q-learning,20,805,0.04100000113248825
Regular Q-learning,20,806,0.03799999877810478
Regular Q-learning,20,807,0.03700000047683716
Regular Q-learning,20,808,0.026000000536441803
Regular Q-learning,20,809,0.04500000178813934
Regular Q-learning,20,810,0.039000000804662704
Regular Q-learning,20,811,0.03799999877810478
Regular Q-learning,20,812,0.026000000536441803
Regular Q-learning,20,813,0.041999999433755875
Regular Q-learning,20,814,0.039000000804662704
Regular Q-learning,20,815,0.03799999877810478
Regular Q-learning,20,816,0.02800000086426735
Regular Q-learning,20,817,0.041999999433755875
Regular Q-learning,20,818,0.03999999910593033
Regular Q-learning,20,819,0.03500000014901161
Regular Q-learning,20,820,0.02800000086426735
Regular Q-learning,20,821,0.0430000014603138
Regular Q-learning,20,822,0.03999999910593033
Regular Q-learning,20,823,0.03400000184774399
Regular Q-learning,20,824,0.026000000536441803
Regular Q-learning,20,825,0.0430000014603138
Regular Q-learning,20,826,0.04100000113248825
Regular Q-learning,20,827,0.03400000184774399
Regular Q-learning,20,828,0.02800000086426735
Regular Q-learning,20,829,0.0430000014603138
Regular Q-learning,20,830,0.04100000113248825
Regular Q-learning,20,831,0.03400000184774399
Regular Q-learning,20,832,0.028999999165534973
Regular Q-learning,20,833,0.041999999433755875
Regular Q-learning,20,834,0.03999999910593033
Regular Q-learning,20,835,0.03400000184774399
Regular Q-learning,20,836,0.028999999165534973
Regular Q-learning,20,837,0.04399999976158142
Regular Q-learning,20,838,0.039000000804662704
Regular Q-learning,20,839,0.035999998450279236
Regular Q-learning,20,840,0.029999999329447746
Regular Q-learning,20,841,0.039000000804662704
Regular Q-learning,20,842,0.03999999910593033
Regular Q-learning,20,843,0.03500000014901161
Regular Q-learning,20,844,0.03099999949336052
Regular Q-learning,20,845,0.03999999910593033
Regular Q-learning,20,846,0.039000000804662704
Regular Q-learning,20,847,0.03400000184774399
Regular Q-learning,20,848,0.032999999821186066
Regular Q-learning,20,849,0.04100000113248825
Regular Q-learning,20,850,0.03700000047683716
Regular Q-learning,20,851,0.032999999821186066
Regular Q-learning,20,852,0.03400000184774399
Regular Q-learning,20,853,0.03999999910593033
Regular Q-learning,20,854,0.039000000804662704
Regular Q-learning,20,855,0.03700000047683716
Regular Q-learning,20,856,0.03500000014901161
Regular Q-learning,20,857,0.039000000804662704
Regular Q-learning,20,858,0.03999999910593033
Regular Q-learning,20,859,0.03400000184774399
Regular Q-learning,20,860,0.03500000014901161
Regular Q-learning,20,861,0.03999999910593033
Regular Q-learning,20,862,0.03700000047683716
Regular Q-learning,20,863,0.035999998450279236
Regular Q-learning,20,864,0.032999999821186066
Regular Q-learning,20,865,0.03700000047683716
Regular Q-learning,20,866,0.039000000804662704
Regular Q-learning,20,867,0.03700000047683716
Regular Q-learning,20,868,0.03099999949336052
Regular Q-learning,20,869,0.03799999877810478
Regular Q-learning,20,870,0.035999998450279236
Regular Q-learning,20,871,0.03999999910593033
Regular Q-learning,20,872,0.032999999821186066
Regular Q-learning,20,873,0.03799999877810478
Regular Q-learning,20,874,0.03500000014901161
Regular Q-learning,20,875,0.03799999877810478
Regular Q-learning,20,876,0.03200000151991844
Regular Q-learning,20,877,0.04100000113248825
Regular Q-learning,20,878,0.03799999877810478
Regular Q-learning,20,879,0.039000000804662704
Regular Q-learning,20,880,0.03099999949336052
Regular Q-learning,20,881,0.03799999877810478
Regular Q-learning,20,882,0.03799999877810478
Regular Q-learning,20,883,0.03700000047683716
Regular Q-learning,20,884,0.028999999165534973
Regular Q-learning,20,885,0.041999999433755875
Regular Q-learning,20,886,0.035999998450279236
Regular Q-learning,20,887,0.03799999877810478
Regular Q-learning,20,888,0.03200000151991844
Regular Q-learning,20,889,0.039000000804662704
Regular Q-learning,20,890,0.032999999821186066
Regular Q-learning,20,891,0.03700000047683716
Regular Q-learning,20,892,0.03400000184774399
Regular Q-learning,20,893,0.041999999433755875
Regular Q-learning,20,894,0.032999999821186066
Regular Q-learning,20,895,0.035999998450279236
Regular Q-learning,20,896,0.03500000014901161
Regular Q-learning,20,897,0.04100000113248825
Regular Q-learning,20,898,0.03200000151991844
Regular Q-learning,20,899,0.03700000047683716
Regular Q-learning,20,900,0.03400000184774399
Regular Q-learning,20,901,0.03999999910593033
Regular Q-learning,20,902,0.032999999821186066
Regular Q-learning,20,903,0.03700000047683716
Regular Q-learning,20,904,0.03400000184774399
Regular Q-learning,20,905,0.039000000804662704
Regular Q-learning,20,906,0.035999998450279236
Regular Q-learning,20,907,0.03500000014901161
Regular Q-learning,20,908,0.027000000700354576
Regular Q-learning,20,909,0.04600000008940697
Regular Q-learning,20,910,0.03400000184774399
Regular Q-learning,20,911,0.032999999821186066
Regular Q-learning,20,912,0.029999999329447746
Regular Q-learning,20,913,0.04600000008940697
Regular Q-learning,20,914,0.03700000047683716
Regular Q-learning,20,915,0.03099999949336052
Regular Q-learning,20,916,0.028999999165534973
Regular Q-learning,20,917,0.0430000014603138
Regular Q-learning,20,918,0.035999998450279236
Regular Q-learning,20,919,0.03099999949336052
Regular Q-learning,20,920,0.028999999165534973
Regular Q-learning,20,921,0.04500000178813934
Regular Q-learning,20,922,0.035999998450279236
Regular Q-learning,20,923,0.02800000086426735
Regular Q-learning,20,924,0.02800000086426735
Regular Q-learning,20,925,0.0430000014603138
Regular Q-learning,20,926,0.03700000047683716
Regular Q-learning,20,927,0.027000000700354576
Regular Q-learning,20,928,0.028999999165534973
Regular Q-learning,20,929,0.04500000178813934
Regular Q-learning,20,930,0.03700000047683716
Regular Q-learning,20,931,0.02800000086426735
Regular Q-learning,20,932,0.03099999949336052
Regular Q-learning,20,933,0.04100000113248825
Regular Q-learning,20,934,0.03799999877810478
Regular Q-learning,20,935,0.029999999329447746
Regular Q-learning,20,936,0.029999999329447746
Regular Q-learning,20,937,0.03999999910593033
Regular Q-learning,20,938,0.03700000047683716
Regular Q-learning,20,939,0.028999999165534973
Regular Q-learning,20,940,0.029999999329447746
Regular Q-learning,20,941,0.03999999910593033
Regular Q-learning,20,942,0.03799999877810478
Regular Q-learning,20,943,0.028999999165534973
Regular Q-learning,20,944,0.028999999165534973
Regular Q-learning,20,945,0.03999999910593033
Regular Q-learning,20,946,0.03700000047683716
Regular Q-learning,20,947,0.03200000151991844
Regular Q-learning,20,948,0.029999999329447746
Regular Q-learning,20,949,0.039000000804662704
Regular Q-learning,20,950,0.03700000047683716
Regular Q-learning,20,951,0.03400000184774399
Regular Q-learning,20,952,0.03099999949336052
Regular Q-learning,20,953,0.039000000804662704
Regular Q-learning,20,954,0.035999998450279236
Regular Q-learning,20,955,0.032999999821186066
Regular Q-learning,20,956,0.03200000151991844
Regular Q-learning,20,957,0.03700000047683716
Regular Q-learning,20,958,0.03400000184774399
Regular Q-learning,20,959,0.03400000184774399
Regular Q-learning,20,960,0.028999999165534973
Regular Q-learning,20,961,0.03799999877810478
Regular Q-learning,20,962,0.03400000184774399
Regular Q-learning,20,963,0.03500000014901161
Regular Q-learning,20,964,0.03099999949336052
Regular Q-learning,20,965,0.03700000047683716
Regular Q-learning,20,966,0.032999999821186066
Regular Q-learning,20,967,0.035999998450279236
Regular Q-learning,20,968,0.03099999949336052
Regular Q-learning,20,969,0.039000000804662704
Regular Q-learning,20,970,0.03400000184774399
Regular Q-learning,20,971,0.03400000184774399
Regular Q-learning,20,972,0.02800000086426735
Regular Q-learning,20,973,0.039000000804662704
Regular Q-learning,20,974,0.03700000047683716
Regular Q-learning,20,975,0.03099999949336052
Regular Q-learning,20,976,0.02800000086426735
Regular Q-learning,20,977,0.03799999877810478
Regular Q-learning,20,978,0.03799999877810478
Regular Q-learning,20,979,0.03200000151991844
Regular Q-learning,20,980,0.029999999329447746
Regular Q-learning,20,981,0.035999998450279236
Regular Q-learning,20,982,0.03700000047683716
Regular Q-learning,20,983,0.03200000151991844
Regular Q-learning,20,984,0.028999999165534973
Regular Q-learning,20,985,0.035999998450279236
Regular Q-learning,20,986,0.03799999877810478
Regular Q-learning,20,987,0.03400000184774399
Regular Q-learning,20,988,0.029999999329447746
Regular Q-learning,20,989,0.03500000014901161
Regular Q-learning,20,990,0.03799999877810478
Regular Q-learning,20,991,0.03500000014901161
Regular Q-learning,20,992,0.028999999165534973
Regular Q-learning,20,993,0.03500000014901161
Regular Q-learning,20,994,0.03700000047683716
Regular Q-learning,20,995,0.035999998450279236
Regular Q-learning,20,996,0.029999999329447746
Regular Q-learning,20,997,0.032999999821186066
Regular Q-learning,20,998,0.03700000047683716
Regular Q-learning,20,999,0.03700000047683716
Regular Q-learning,20,1000,0.02800000086426735
Regular Q-learning,50,1,0.2669999897480011
Regular Q-learning,50,2,0.22200000286102295
Regular Q-learning,50,3,0.17499999701976776
Regular Q-learning,50,4,0.1459999978542328
Regular Q-learning,50,5,0.12999999523162842
Regular Q-learning,50,6,0.12700000405311584
Regular Q-learning,50,7,0.11100000143051147
Regular Q-learning,50,8,0.10999999940395355
Regular Q-learning,50,9,0.11500000208616257
Regular Q-learning,50,10,0.11500000208616257
Regular Q-learning,50,11,0.125
Regular Q-learning,50,12,0.12600000202655792
Regular Q-learning,50,13,0.14100000262260437
Regular Q-learning,50,14,0.12600000202655792
Regular Q-learning,50,15,0.12999999523162842
Regular Q-learning,50,16,0.12999999523162842
Regular Q-learning,50,17,0.12200000137090683
Regular Q-learning,50,18,0.1340000033378601
Regular Q-learning,50,19,0.12800000607967377
Regular Q-learning,50,20,0.12399999797344208
Regular Q-learning,50,21,0.12200000137090683
Regular Q-learning,50,22,0.1120000034570694
Regular Q-learning,50,23,0.12200000137090683
Regular Q-learning,50,24,0.1120000034570694
Regular Q-learning,50,25,0.11900000274181366
Regular Q-learning,50,26,0.11400000005960464
Regular Q-learning,50,27,0.10700000077486038
Regular Q-learning,50,28,0.1080000028014183
Regular Q-learning,50,29,0.10999999940395355
Regular Q-learning,50,30,0.09300000220537186
Regular Q-learning,50,31,0.09600000083446503
Regular Q-learning,50,32,0.10100000351667404
Regular Q-learning,50,33,0.10400000214576721
Regular Q-learning,50,34,0.08799999952316284
Regular Q-learning,50,35,0.09799999743700027
Regular Q-learning,50,36,0.08500000089406967
Regular Q-learning,50,37,0.09799999743700027
Regular Q-learning,50,38,0.08799999952316284
Regular Q-learning,50,39,0.08500000089406967
Regular Q-learning,50,40,0.08299999684095383
Regular Q-learning,50,41,0.0860000029206276
Regular Q-learning,50,42,0.07800000160932541
Regular Q-learning,50,43,0.07800000160932541
Regular Q-learning,50,44,0.07400000095367432
Regular Q-learning,50,45,0.07800000160932541
Regular Q-learning,50,46,0.07699999958276749
Regular Q-learning,50,47,0.07199999690055847
Regular Q-learning,50,48,0.0689999982714653
Regular Q-learning,50,49,0.07500000298023224
Regular Q-learning,50,50,0.06599999964237213
Regular Q-learning,50,51,0.07000000029802322
Regular Q-learning,50,52,0.07199999690055847
Regular Q-learning,50,53,0.07000000029802322
Regular Q-learning,50,54,0.06800000369548798
Regular Q-learning,50,55,0.06700000166893005
Regular Q-learning,50,56,0.06800000369548798
Regular Q-learning,50,57,0.0689999982714653
Regular Q-learning,50,58,0.06599999964237213
Regular Q-learning,50,59,0.06800000369548798
Regular Q-learning,50,60,0.061000000685453415
Regular Q-learning,50,61,0.05999999865889549
Regular Q-learning,50,62,0.061000000685453415
Regular Q-learning,50,63,0.06199999898672104
Regular Q-learning,50,64,0.06199999898672104
Regular Q-learning,50,65,0.06800000369548798
Regular Q-learning,50,66,0.061000000685453415
Regular Q-learning,50,67,0.06800000369548798
Regular Q-learning,50,68,0.05400000140070915
Regular Q-learning,50,69,0.0560000017285347
Regular Q-learning,50,70,0.06199999898672104
Regular Q-learning,50,71,0.061000000685453415
Regular Q-learning,50,72,0.06199999898672104
Regular Q-learning,50,73,0.0560000017285347
Regular Q-learning,50,74,0.057999998331069946
Regular Q-learning,50,75,0.061000000685453415
Regular Q-learning,50,76,0.057999998331069946
Regular Q-learning,50,77,0.05999999865889549
Regular Q-learning,50,78,0.0560000017285347
Regular Q-learning,50,79,0.05900000035762787
Regular Q-learning,50,80,0.05700000002980232
Regular Q-learning,50,81,0.057999998331069946
Regular Q-learning,50,82,0.054999999701976776
Regular Q-learning,50,83,0.05900000035762787
Regular Q-learning,50,84,0.05299999937415123
Regular Q-learning,50,85,0.06199999898672104
Regular Q-learning,50,86,0.052000001072883606
Regular Q-learning,50,87,0.05999999865889549
Regular Q-learning,50,88,0.05299999937415123
Regular Q-learning,50,89,0.05999999865889549
Regular Q-learning,50,90,0.05700000002980232
Regular Q-learning,50,91,0.05700000002980232
Regular Q-learning,50,92,0.05000000074505806
Regular Q-learning,50,93,0.05999999865889549
Regular Q-learning,50,94,0.050999999046325684
Regular Q-learning,50,95,0.05900000035762787
Regular Q-learning,50,96,0.04600000008940697
Regular Q-learning,50,97,0.054999999701976776
Regular Q-learning,50,98,0.050999999046325684
Regular Q-learning,50,99,0.061000000685453415
Regular Q-learning,50,100,0.04899999871850014
Regular Q-learning,50,101,0.050999999046325684
Regular Q-learning,50,102,0.05299999937415123
Regular Q-learning,50,103,0.054999999701976776
Regular Q-learning,50,104,0.04699999839067459
Regular Q-learning,50,105,0.057999998331069946
Regular Q-learning,50,106,0.054999999701976776
Regular Q-learning,50,107,0.06199999898672104
Regular Q-learning,50,108,0.04600000008940697
Regular Q-learning,50,109,0.05299999937415123
Regular Q-learning,50,110,0.05000000074505806
Regular Q-learning,50,111,0.0560000017285347
Regular Q-learning,50,112,0.04899999871850014
Regular Q-learning,50,113,0.04899999871850014
Regular Q-learning,50,114,0.04800000041723251
Regular Q-learning,50,115,0.0560000017285347
Regular Q-learning,50,116,0.04699999839067459
Regular Q-learning,50,117,0.0560000017285347
Regular Q-learning,50,118,0.04500000178813934
Regular Q-learning,50,119,0.05700000002980232
Regular Q-learning,50,120,0.04699999839067459
Regular Q-learning,50,121,0.050999999046325684
Regular Q-learning,50,122,0.04699999839067459
Regular Q-learning,50,123,0.0560000017285347
Regular Q-learning,50,124,0.04399999976158142
Regular Q-learning,50,125,0.05299999937415123
Regular Q-learning,50,126,0.04800000041723251
Regular Q-learning,50,127,0.050999999046325684
Regular Q-learning,50,128,0.04500000178813934
Regular Q-learning,50,129,0.05299999937415123
Regular Q-learning,50,130,0.04699999839067459
Regular Q-learning,50,131,0.054999999701976776
Regular Q-learning,50,132,0.04699999839067459
Regular Q-learning,50,133,0.05000000074505806
Regular Q-learning,50,134,0.04399999976158142
Regular Q-learning,50,135,0.05299999937415123
Regular Q-learning,50,136,0.04600000008940697
Regular Q-learning,50,137,0.05400000140070915
Regular Q-learning,50,138,0.04699999839067459
Regular Q-learning,50,139,0.05400000140070915
Regular Q-learning,50,140,0.04699999839067459
Regular Q-learning,50,141,0.050999999046325684
Regular Q-learning,50,142,0.04399999976158142
Regular Q-learning,50,143,0.050999999046325684
Regular Q-learning,50,144,0.039000000804662704
Regular Q-learning,50,145,0.05400000140070915
Regular Q-learning,50,146,0.04399999976158142
Regular Q-learning,50,147,0.05299999937415123
Regular Q-learning,50,148,0.04399999976158142
Regular Q-learning,50,149,0.054999999701976776
Regular Q-learning,50,150,0.04500000178813934
Regular Q-learning,50,151,0.05000000074505806
Regular Q-learning,50,152,0.0430000014603138
Regular Q-learning,50,153,0.05299999937415123
Regular Q-learning,50,154,0.0430000014603138
Regular Q-learning,50,155,0.052000001072883606
Regular Q-learning,50,156,0.04500000178813934
Regular Q-learning,50,157,0.050999999046325684
Regular Q-learning,50,158,0.041999999433755875
Regular Q-learning,50,159,0.05299999937415123
Regular Q-learning,50,160,0.04500000178813934
Regular Q-learning,50,161,0.050999999046325684
Regular Q-learning,50,162,0.04500000178813934
Regular Q-learning,50,163,0.04899999871850014
Regular Q-learning,50,164,0.0430000014603138
Regular Q-learning,50,165,0.04899999871850014
Regular Q-learning,50,166,0.041999999433755875
Regular Q-learning,50,167,0.050999999046325684
Regular Q-learning,50,168,0.04399999976158142
Regular Q-learning,50,169,0.04899999871850014
Regular Q-learning,50,170,0.04600000008940697
Regular Q-learning,50,171,0.04800000041723251
Regular Q-learning,50,172,0.04800000041723251
Regular Q-learning,50,173,0.05000000074505806
Regular Q-learning,50,174,0.0430000014603138
Regular Q-learning,50,175,0.04800000041723251
Regular Q-learning,50,176,0.04500000178813934
Regular Q-learning,50,177,0.04500000178813934
Regular Q-learning,50,178,0.04600000008940697
Regular Q-learning,50,179,0.04600000008940697
Regular Q-learning,50,180,0.04500000178813934
Regular Q-learning,50,181,0.04899999871850014
Regular Q-learning,50,182,0.0430000014603138
Regular Q-learning,50,183,0.05000000074505806
Regular Q-learning,50,184,0.04600000008940697
Regular Q-learning,50,185,0.04600000008940697
Regular Q-learning,50,186,0.04100000113248825
Regular Q-learning,50,187,0.05000000074505806
Regular Q-learning,50,188,0.04500000178813934
Regular Q-learning,50,189,0.052000001072883606
Regular Q-learning,50,190,0.04399999976158142
Regular Q-learning,50,191,0.05000000074505806
Regular Q-learning,50,192,0.04500000178813934
Regular Q-learning,50,193,0.050999999046325684
Regular Q-learning,50,194,0.04100000113248825
Regular Q-learning,50,195,0.04899999871850014
Regular Q-learning,50,196,0.04600000008940697
Regular Q-learning,50,197,0.04899999871850014
Regular Q-learning,50,198,0.04500000178813934
Regular Q-learning,50,199,0.04600000008940697
Regular Q-learning,50,200,0.04100000113248825
Regular Q-learning,50,201,0.04899999871850014
Regular Q-learning,50,202,0.04399999976158142
Regular Q-learning,50,203,0.039000000804662704
Regular Q-learning,50,204,0.041999999433755875
Regular Q-learning,50,205,0.04800000041723251
Regular Q-learning,50,206,0.0430000014603138
Regular Q-learning,50,207,0.04399999976158142
Regular Q-learning,50,208,0.04500000178813934
Regular Q-learning,50,209,0.04699999839067459
Regular Q-learning,50,210,0.04100000113248825
Regular Q-learning,50,211,0.0430000014603138
Regular Q-learning,50,212,0.04399999976158142
Regular Q-learning,50,213,0.04399999976158142
Regular Q-learning,50,214,0.0430000014603138
Regular Q-learning,50,215,0.04600000008940697
Regular Q-learning,50,216,0.0430000014603138
Regular Q-learning,50,217,0.04800000041723251
Regular Q-learning,50,218,0.03799999877810478
Regular Q-learning,50,219,0.0430000014603138
Regular Q-learning,50,220,0.04399999976158142
Regular Q-learning,50,221,0.04500000178813934
Regular Q-learning,50,222,0.03799999877810478
Regular Q-learning,50,223,0.04600000008940697
Regular Q-learning,50,224,0.04100000113248825
Regular Q-learning,50,225,0.04500000178813934
Regular Q-learning,50,226,0.04100000113248825
Regular Q-learning,50,227,0.04600000008940697
Regular Q-learning,50,228,0.0430000014603138
Regular Q-learning,50,229,0.04500000178813934
Regular Q-learning,50,230,0.039000000804662704
Regular Q-learning,50,231,0.04699999839067459
Regular Q-learning,50,232,0.039000000804662704
Regular Q-learning,50,233,0.04600000008940697
Regular Q-learning,50,234,0.03799999877810478
Regular Q-learning,50,235,0.04699999839067459
Regular Q-learning,50,236,0.04100000113248825
Regular Q-learning,50,237,0.04500000178813934
Regular Q-learning,50,238,0.035999998450279236
Regular Q-learning,50,239,0.04699999839067459
Regular Q-learning,50,240,0.039000000804662704
Regular Q-learning,50,241,0.04899999871850014
Regular Q-learning,50,242,0.03799999877810478
Regular Q-learning,50,243,0.04500000178813934
Regular Q-learning,50,244,0.039000000804662704
Regular Q-learning,50,245,0.04899999871850014
Regular Q-learning,50,246,0.03700000047683716
Regular Q-learning,50,247,0.04899999871850014
Regular Q-learning,50,248,0.039000000804662704
Regular Q-learning,50,249,0.05000000074505806
Regular Q-learning,50,250,0.03400000184774399
Regular Q-learning,50,251,0.04699999839067459
Regular Q-learning,50,252,0.03500000014901161
Regular Q-learning,50,253,0.050999999046325684
Regular Q-learning,50,254,0.03500000014901161
Regular Q-learning,50,255,0.050999999046325684
Regular Q-learning,50,256,0.03200000151991844
Regular Q-learning,50,257,0.05000000074505806
Regular Q-learning,50,258,0.03500000014901161
Regular Q-learning,50,259,0.04899999871850014
Regular Q-learning,50,260,0.03799999877810478
Regular Q-learning,50,261,0.04899999871850014
Regular Q-learning,50,262,0.03500000014901161
Regular Q-learning,50,263,0.04899999871850014
Regular Q-learning,50,264,0.035999998450279236
Regular Q-learning,50,265,0.04699999839067459
Regular Q-learning,50,266,0.039000000804662704
Regular Q-learning,50,267,0.04899999871850014
Regular Q-learning,50,268,0.032999999821186066
Regular Q-learning,50,269,0.05299999937415123
Regular Q-learning,50,270,0.03799999877810478
Regular Q-learning,50,271,0.052000001072883606
Regular Q-learning,50,272,0.03099999949336052
Regular Q-learning,50,273,0.05000000074505806
Regular Q-learning,50,274,0.03700000047683716
Regular Q-learning,50,275,0.04800000041723251
Regular Q-learning,50,276,0.029999999329447746
Regular Q-learning,50,277,0.05299999937415123
Regular Q-learning,50,278,0.03200000151991844
Regular Q-learning,50,279,0.05000000074505806
Regular Q-learning,50,280,0.03400000184774399
Regular Q-learning,50,281,0.04899999871850014
Regular Q-learning,50,282,0.03500000014901161
Regular Q-learning,50,283,0.04699999839067459
Regular Q-learning,50,284,0.029999999329447746
Regular Q-learning,50,285,0.05400000140070915
Regular Q-learning,50,286,0.03400000184774399
Regular Q-learning,50,287,0.05000000074505806
Regular Q-learning,50,288,0.028999999165534973
Regular Q-learning,50,289,0.05000000074505806
Regular Q-learning,50,290,0.03099999949336052
Regular Q-learning,50,291,0.04800000041723251
Regular Q-learning,50,292,0.03200000151991844
Regular Q-learning,50,293,0.052000001072883606
Regular Q-learning,50,294,0.03400000184774399
Regular Q-learning,50,295,0.04800000041723251
Regular Q-learning,50,296,0.032999999821186066
Regular Q-learning,50,297,0.052000001072883606
Regular Q-learning,50,298,0.03400000184774399
Regular Q-learning,50,299,0.05000000074505806
Regular Q-learning,50,300,0.03200000151991844
Regular Q-learning,50,301,0.04600000008940697
Regular Q-learning,50,302,0.03999999910593033
Regular Q-learning,50,303,0.0430000014603138
Regular Q-learning,50,304,0.02800000086426735
Regular Q-learning,50,305,0.052000001072883606
Regular Q-learning,50,306,0.04100000113248825
Regular Q-learning,50,307,0.04699999839067459
Regular Q-learning,50,308,0.03200000151991844
Regular Q-learning,50,309,0.04699999839067459
Regular Q-learning,50,310,0.035999998450279236
Regular Q-learning,50,311,0.052000001072883606
Regular Q-learning,50,312,0.03099999949336052
Regular Q-learning,50,313,0.04500000178813934
Regular Q-learning,50,314,0.03700000047683716
Regular Q-learning,50,315,0.0430000014603138
Regular Q-learning,50,316,0.028999999165534973
Regular Q-learning,50,317,0.04800000041723251
Regular Q-learning,50,318,0.039000000804662704
Regular Q-learning,50,319,0.04600000008940697
Regular Q-learning,50,320,0.03500000014901161
Regular Q-learning,50,321,0.04399999976158142
Regular Q-learning,50,322,0.03500000014901161
Regular Q-learning,50,323,0.05000000074505806
Regular Q-learning,50,324,0.03500000014901161
Regular Q-learning,50,325,0.04399999976158142
Regular Q-learning,50,326,0.03500000014901161
Regular Q-learning,50,327,0.04800000041723251
Regular Q-learning,50,328,0.03200000151991844
Regular Q-learning,50,329,0.041999999433755875
Regular Q-learning,50,330,0.03799999877810478
Regular Q-learning,50,331,0.04500000178813934
Regular Q-learning,50,332,0.029999999329447746
Regular Q-learning,50,333,0.04500000178813934
Regular Q-learning,50,334,0.03700000047683716
Regular Q-learning,50,335,0.0430000014603138
Regular Q-learning,50,336,0.03400000184774399
Regular Q-learning,50,337,0.050999999046325684
Regular Q-learning,50,338,0.03400000184774399
Regular Q-learning,50,339,0.04500000178813934
Regular Q-learning,50,340,0.03400000184774399
Regular Q-learning,50,341,0.04699999839067459
Regular Q-learning,50,342,0.03500000014901161
Regular Q-learning,50,343,0.0430000014603138
Regular Q-learning,50,344,0.03700000047683716
Regular Q-learning,50,345,0.04600000008940697
Regular Q-learning,50,346,0.03200000151991844
Regular Q-learning,50,347,0.04800000041723251
Regular Q-learning,50,348,0.03700000047683716
Regular Q-learning,50,349,0.03999999910593033
Regular Q-learning,50,350,0.03799999877810478
Regular Q-learning,50,351,0.04800000041723251
Regular Q-learning,50,352,0.032999999821186066
Regular Q-learning,50,353,0.04500000178813934
Regular Q-learning,50,354,0.03500000014901161
Regular Q-learning,50,355,0.04500000178813934
Regular Q-learning,50,356,0.03700000047683716
Regular Q-learning,50,357,0.04800000041723251
Regular Q-learning,50,358,0.03200000151991844
Regular Q-learning,50,359,0.04399999976158142
Regular Q-learning,50,360,0.03700000047683716
Regular Q-learning,50,361,0.041999999433755875
Regular Q-learning,50,362,0.03500000014901161
Regular Q-learning,50,363,0.04500000178813934
Regular Q-learning,50,364,0.035999998450279236
Regular Q-learning,50,365,0.04600000008940697
Regular Q-learning,50,366,0.03700000047683716
Regular Q-learning,50,367,0.04399999976158142
Regular Q-learning,50,368,0.035999998450279236
Regular Q-learning,50,369,0.041999999433755875
Regular Q-learning,50,370,0.032999999821186066
Regular Q-learning,50,371,0.0430000014603138
Regular Q-learning,50,372,0.03400000184774399
Regular Q-learning,50,373,0.04600000008940697
Regular Q-learning,50,374,0.03200000151991844
Regular Q-learning,50,375,0.04399999976158142
Regular Q-learning,50,376,0.03799999877810478
Regular Q-learning,50,377,0.041999999433755875
Regular Q-learning,50,378,0.03400000184774399
Regular Q-learning,50,379,0.04600000008940697
Regular Q-learning,50,380,0.035999998450279236
Regular Q-learning,50,381,0.04399999976158142
Regular Q-learning,50,382,0.03200000151991844
Regular Q-learning,50,383,0.04500000178813934
Regular Q-learning,50,384,0.032999999821186066
Regular Q-learning,50,385,0.04500000178813934
Regular Q-learning,50,386,0.03400000184774399
Regular Q-learning,50,387,0.04399999976158142
Regular Q-learning,50,388,0.03400000184774399
Regular Q-learning,50,389,0.04699999839067459
Regular Q-learning,50,390,0.03200000151991844
Regular Q-learning,50,391,0.04399999976158142
Regular Q-learning,50,392,0.03200000151991844
Regular Q-learning,50,393,0.04899999871850014
Regular Q-learning,50,394,0.03500000014901161
Regular Q-learning,50,395,0.03999999910593033
Regular Q-learning,50,396,0.03099999949336052
Regular Q-learning,50,397,0.04899999871850014
Regular Q-learning,50,398,0.03200000151991844
Regular Q-learning,50,399,0.04399999976158142
Regular Q-learning,50,400,0.03400000184774399
Regular Q-learning,50,401,0.05000000074505806
Regular Q-learning,50,402,0.035999998450279236
Regular Q-learning,50,403,0.0430000014603138
Regular Q-learning,50,404,0.03200000151991844
Regular Q-learning,50,405,0.04899999871850014
Regular Q-learning,50,406,0.03200000151991844
Regular Q-learning,50,407,0.03999999910593033
Regular Q-learning,50,408,0.035999998450279236
Regular Q-learning,50,409,0.04399999976158142
Regular Q-learning,50,410,0.032999999821186066
Regular Q-learning,50,411,0.04100000113248825
Regular Q-learning,50,412,0.03700000047683716
Regular Q-learning,50,413,0.04399999976158142
Regular Q-learning,50,414,0.03099999949336052
Regular Q-learning,50,415,0.0430000014603138
Regular Q-learning,50,416,0.03500000014901161
Regular Q-learning,50,417,0.0430000014603138
Regular Q-learning,50,418,0.035999998450279236
Regular Q-learning,50,419,0.04399999976158142
Regular Q-learning,50,420,0.03400000184774399
Regular Q-learning,50,421,0.04500000178813934
Regular Q-learning,50,422,0.032999999821186066
Regular Q-learning,50,423,0.0430000014603138
Regular Q-learning,50,424,0.03700000047683716
Regular Q-learning,50,425,0.04500000178813934
Regular Q-learning,50,426,0.03200000151991844
Regular Q-learning,50,427,0.04699999839067459
Regular Q-learning,50,428,0.03200000151991844
Regular Q-learning,50,429,0.04600000008940697
Regular Q-learning,50,430,0.03200000151991844
Regular Q-learning,50,431,0.04500000178813934
Regular Q-learning,50,432,0.032999999821186066
Regular Q-learning,50,433,0.04399999976158142
Regular Q-learning,50,434,0.032999999821186066
Regular Q-learning,50,435,0.04399999976158142
Regular Q-learning,50,436,0.03500000014901161
Regular Q-learning,50,437,0.04399999976158142
Regular Q-learning,50,438,0.03400000184774399
Regular Q-learning,50,439,0.04699999839067459
Regular Q-learning,50,440,0.03500000014901161
Regular Q-learning,50,441,0.03999999910593033
Regular Q-learning,50,442,0.03500000014901161
Regular Q-learning,50,443,0.0430000014603138
Regular Q-learning,50,444,0.03700000047683716
Regular Q-learning,50,445,0.04500000178813934
Regular Q-learning,50,446,0.02800000086426735
Regular Q-learning,50,447,0.041999999433755875
Regular Q-learning,50,448,0.03999999910593033
Regular Q-learning,50,449,0.04399999976158142
Regular Q-learning,50,450,0.029999999329447746
Regular Q-learning,50,451,0.04100000113248825
Regular Q-learning,50,452,0.03700000047683716
Regular Q-learning,50,453,0.04800000041723251
Regular Q-learning,50,454,0.029999999329447746
Regular Q-learning,50,455,0.03799999877810478
Regular Q-learning,50,456,0.03700000047683716
Regular Q-learning,50,457,0.04600000008940697
Regular Q-learning,50,458,0.028999999165534973
Regular Q-learning,50,459,0.041999999433755875
Regular Q-learning,50,460,0.035999998450279236
Regular Q-learning,50,461,0.04800000041723251
Regular Q-learning,50,462,0.03099999949336052
Regular Q-learning,50,463,0.039000000804662704
Regular Q-learning,50,464,0.032999999821186066
Regular Q-learning,50,465,0.05000000074505806
Regular Q-learning,50,466,0.029999999329447746
Regular Q-learning,50,467,0.0430000014603138
Regular Q-learning,50,468,0.03700000047683716
Regular Q-learning,50,469,0.04500000178813934
Regular Q-learning,50,470,0.029999999329447746
Regular Q-learning,50,471,0.04100000113248825
Regular Q-learning,50,472,0.03799999877810478
Regular Q-learning,50,473,0.0430000014603138
Regular Q-learning,50,474,0.032999999821186066
Regular Q-learning,50,475,0.03999999910593033
Regular Q-learning,50,476,0.03799999877810478
Regular Q-learning,50,477,0.04500000178813934
Regular Q-learning,50,478,0.03400000184774399
Regular Q-learning,50,479,0.0430000014603138
Regular Q-learning,50,480,0.032999999821186066
Regular Q-learning,50,481,0.04800000041723251
Regular Q-learning,50,482,0.03099999949336052
Regular Q-learning,50,483,0.03700000047683716
Regular Q-learning,50,484,0.03099999949336052
Regular Q-learning,50,485,0.04800000041723251
Regular Q-learning,50,486,0.03400000184774399
Regular Q-learning,50,487,0.04100000113248825
Regular Q-learning,50,488,0.03400000184774399
Regular Q-learning,50,489,0.04699999839067459
Regular Q-learning,50,490,0.03099999949336052
Regular Q-learning,50,491,0.041999999433755875
Regular Q-learning,50,492,0.03500000014901161
Regular Q-learning,50,493,0.04800000041723251
Regular Q-learning,50,494,0.032999999821186066
Regular Q-learning,50,495,0.041999999433755875
Regular Q-learning,50,496,0.032999999821186066
Regular Q-learning,50,497,0.04699999839067459
Regular Q-learning,50,498,0.035999998450279236
Regular Q-learning,50,499,0.0430000014603138
Regular Q-learning,50,500,0.03200000151991844
Regular Q-learning,50,501,0.04899999871850014
Regular Q-learning,50,502,0.029999999329447746
Regular Q-learning,50,503,0.03999999910593033
Regular Q-learning,50,504,0.035999998450279236
Regular Q-learning,50,505,0.04699999839067459
Regular Q-learning,50,506,0.028999999165534973
Regular Q-learning,50,507,0.04600000008940697
Regular Q-learning,50,508,0.039000000804662704
Regular Q-learning,50,509,0.04500000178813934
Regular Q-learning,50,510,0.028999999165534973
Regular Q-learning,50,511,0.0430000014603138
Regular Q-learning,50,512,0.03999999910593033
Regular Q-learning,50,513,0.04399999976158142
Regular Q-learning,50,514,0.03500000014901161
Regular Q-learning,50,515,0.041999999433755875
Regular Q-learning,50,516,0.03799999877810478
Regular Q-learning,50,517,0.04399999976158142
Regular Q-learning,50,518,0.03099999949336052
Regular Q-learning,50,519,0.041999999433755875
Regular Q-learning,50,520,0.039000000804662704
Regular Q-learning,50,521,0.0430000014603138
Regular Q-learning,50,522,0.03099999949336052
Regular Q-learning,50,523,0.04399999976158142
Regular Q-learning,50,524,0.039000000804662704
Regular Q-learning,50,525,0.039000000804662704
Regular Q-learning,50,526,0.03500000014901161
Regular Q-learning,50,527,0.04500000178813934
Regular Q-learning,50,528,0.03500000014901161
Regular Q-learning,50,529,0.04100000113248825
Regular Q-learning,50,530,0.029999999329447746
Regular Q-learning,50,531,0.04100000113248825
Regular Q-learning,50,532,0.035999998450279236
Regular Q-learning,50,533,0.04600000008940697
Regular Q-learning,50,534,0.03099999949336052
Regular Q-learning,50,535,0.03999999910593033
Regular Q-learning,50,536,0.03700000047683716
Regular Q-learning,50,537,0.04399999976158142
Regular Q-learning,50,538,0.03200000151991844
Regular Q-learning,50,539,0.03700000047683716
Regular Q-learning,50,540,0.03700000047683716
Regular Q-learning,50,541,0.041999999433755875
Regular Q-learning,50,542,0.03099999949336052
Regular Q-learning,50,543,0.04100000113248825
Regular Q-learning,50,544,0.035999998450279236
Regular Q-learning,50,545,0.04399999976158142
Regular Q-learning,50,546,0.03200000151991844
Regular Q-learning,50,547,0.04399999976158142
Regular Q-learning,50,548,0.03700000047683716
Regular Q-learning,50,549,0.039000000804662704
Regular Q-learning,50,550,0.03200000151991844
Regular Q-learning,50,551,0.041999999433755875
Regular Q-learning,50,552,0.04100000113248825
Regular Q-learning,50,553,0.039000000804662704
Regular Q-learning,50,554,0.02800000086426735
Regular Q-learning,50,555,0.04399999976158142
Regular Q-learning,50,556,0.03500000014901161
Regular Q-learning,50,557,0.04399999976158142
Regular Q-learning,50,558,0.028999999165534973
Regular Q-learning,50,559,0.04800000041723251
Regular Q-learning,50,560,0.03400000184774399
Regular Q-learning,50,561,0.03700000047683716
Regular Q-learning,50,562,0.029999999329447746
Regular Q-learning,50,563,0.04899999871850014
Regular Q-learning,50,564,0.028999999165534973
Regular Q-learning,50,565,0.03799999877810478
Regular Q-learning,50,566,0.03500000014901161
Regular Q-learning,50,567,0.04600000008940697
Regular Q-learning,50,568,0.028999999165534973
Regular Q-learning,50,569,0.03700000047683716
Regular Q-learning,50,570,0.035999998450279236
Regular Q-learning,50,571,0.04699999839067459
Regular Q-learning,50,572,0.02800000086426735
Regular Q-learning,50,573,0.03700000047683716
Regular Q-learning,50,574,0.03400000184774399
Regular Q-learning,50,575,0.04699999839067459
Regular Q-learning,50,576,0.03099999949336052
Regular Q-learning,50,577,0.03400000184774399
Regular Q-learning,50,578,0.03400000184774399
Regular Q-learning,50,579,0.04699999839067459
Regular Q-learning,50,580,0.029999999329447746
Regular Q-learning,50,581,0.039000000804662704
Regular Q-learning,50,582,0.03700000047683716
Regular Q-learning,50,583,0.04600000008940697
Regular Q-learning,50,584,0.028999999165534973
Regular Q-learning,50,585,0.03400000184774399
Regular Q-learning,50,586,0.03200000151991844
Regular Q-learning,50,587,0.04800000041723251
Regular Q-learning,50,588,0.03099999949336052
Regular Q-learning,50,589,0.03500000014901161
Regular Q-learning,50,590,0.03400000184774399
Regular Q-learning,50,591,0.04899999871850014
Regular Q-learning,50,592,0.03099999949336052
Regular Q-learning,50,593,0.03500000014901161
Regular Q-learning,50,594,0.032999999821186066
Regular Q-learning,50,595,0.04899999871850014
Regular Q-learning,50,596,0.03099999949336052
Regular Q-learning,50,597,0.032999999821186066
Regular Q-learning,50,598,0.032999999821186066
Regular Q-learning,50,599,0.04699999839067459
Regular Q-learning,50,600,0.035999998450279236
Regular Q-learning,50,601,0.03700000047683716
Regular Q-learning,50,602,0.029999999329447746
Regular Q-learning,50,603,0.04800000041723251
Regular Q-learning,50,604,0.03200000151991844
Regular Q-learning,50,605,0.039000000804662704
Regular Q-learning,50,606,0.028999999165534973
Regular Q-learning,50,607,0.04800000041723251
Regular Q-learning,50,608,0.03400000184774399
Regular Q-learning,50,609,0.035999998450279236
Regular Q-learning,50,610,0.03200000151991844
Regular Q-learning,50,611,0.04399999976158142
Regular Q-learning,50,612,0.032999999821186066
Regular Q-learning,50,613,0.03700000047683716
Regular Q-learning,50,614,0.035999998450279236
Regular Q-learning,50,615,0.04500000178813934
Regular Q-learning,50,616,0.032999999821186066
Regular Q-learning,50,617,0.035999998450279236
Regular Q-learning,50,618,0.032999999821186066
Regular Q-learning,50,619,0.04600000008940697
Regular Q-learning,50,620,0.03099999949336052
Regular Q-learning,50,621,0.03700000047683716
Regular Q-learning,50,622,0.03200000151991844
Regular Q-learning,50,623,0.04500000178813934
Regular Q-learning,50,624,0.03400000184774399
Regular Q-learning,50,625,0.03999999910593033
Regular Q-learning,50,626,0.035999998450279236
Regular Q-learning,50,627,0.04100000113248825
Regular Q-learning,50,628,0.03400000184774399
Regular Q-learning,50,629,0.03999999910593033
Regular Q-learning,50,630,0.03500000014901161
Regular Q-learning,50,631,0.03999999910593033
Regular Q-learning,50,632,0.03200000151991844
Regular Q-learning,50,633,0.039000000804662704
Regular Q-learning,50,634,0.03400000184774399
Regular Q-learning,50,635,0.04100000113248825
Regular Q-learning,50,636,0.03099999949336052
Regular Q-learning,50,637,0.03799999877810478
Regular Q-learning,50,638,0.03500000014901161
Regular Q-learning,50,639,0.041999999433755875
Regular Q-learning,50,640,0.03200000151991844
Regular Q-learning,50,641,0.04100000113248825
Regular Q-learning,50,642,0.032999999821186066
Regular Q-learning,50,643,0.03999999910593033
Regular Q-learning,50,644,0.03400000184774399
Regular Q-learning,50,645,0.03999999910593033
Regular Q-learning,50,646,0.029999999329447746
Regular Q-learning,50,647,0.04100000113248825
Regular Q-learning,50,648,0.03500000014901161
Regular Q-learning,50,649,0.04100000113248825
Regular Q-learning,50,650,0.03400000184774399
Regular Q-learning,50,651,0.0430000014603138
Regular Q-learning,50,652,0.03200000151991844
Regular Q-learning,50,653,0.03700000047683716
Regular Q-learning,50,654,0.03400000184774399
Regular Q-learning,50,655,0.0430000014603138
Regular Q-learning,50,656,0.03400000184774399
Regular Q-learning,50,657,0.03799999877810478
Regular Q-learning,50,658,0.03400000184774399
Regular Q-learning,50,659,0.04100000113248825
Regular Q-learning,50,660,0.032999999821186066
Regular Q-learning,50,661,0.03799999877810478
Regular Q-learning,50,662,0.03400000184774399
Regular Q-learning,50,663,0.04399999976158142
Regular Q-learning,50,664,0.03400000184774399
Regular Q-learning,50,665,0.03799999877810478
Regular Q-learning,50,666,0.032999999821186066
Regular Q-learning,50,667,0.04399999976158142
Regular Q-learning,50,668,0.032999999821186066
Regular Q-learning,50,669,0.039000000804662704
Regular Q-learning,50,670,0.03099999949336052
Regular Q-learning,50,671,0.0430000014603138
Regular Q-learning,50,672,0.035999998450279236
Regular Q-learning,50,673,0.039000000804662704
Regular Q-learning,50,674,0.03099999949336052
Regular Q-learning,50,675,0.039000000804662704
Regular Q-learning,50,676,0.03700000047683716
Regular Q-learning,50,677,0.03799999877810478
Regular Q-learning,50,678,0.03400000184774399
Regular Q-learning,50,679,0.03999999910593033
Regular Q-learning,50,680,0.03400000184774399
Regular Q-learning,50,681,0.039000000804662704
Regular Q-learning,50,682,0.032999999821186066
Regular Q-learning,50,683,0.03999999910593033
Regular Q-learning,50,684,0.03400000184774399
Regular Q-learning,50,685,0.039000000804662704
Regular Q-learning,50,686,0.03500000014901161
Regular Q-learning,50,687,0.04100000113248825
Regular Q-learning,50,688,0.03400000184774399
Regular Q-learning,50,689,0.03999999910593033
Regular Q-learning,50,690,0.032999999821186066
Regular Q-learning,50,691,0.03799999877810478
Regular Q-learning,50,692,0.035999998450279236
Regular Q-learning,50,693,0.04399999976158142
Regular Q-learning,50,694,0.03099999949336052
Regular Q-learning,50,695,0.03700000047683716
Regular Q-learning,50,696,0.03500000014901161
Regular Q-learning,50,697,0.041999999433755875
Regular Q-learning,50,698,0.032999999821186066
Regular Q-learning,50,699,0.03700000047683716
Regular Q-learning,50,700,0.03400000184774399
Regular Q-learning,50,701,0.04100000113248825
Regular Q-learning,50,702,0.02800000086426735
Regular Q-learning,50,703,0.04100000113248825
Regular Q-learning,50,704,0.03999999910593033
Regular Q-learning,50,705,0.035999998450279236
Regular Q-learning,50,706,0.027000000700354576
Regular Q-learning,50,707,0.041999999433755875
Regular Q-learning,50,708,0.039000000804662704
Regular Q-learning,50,709,0.03799999877810478
Regular Q-learning,50,710,0.027000000700354576
Regular Q-learning,50,711,0.041999999433755875
Regular Q-learning,50,712,0.03799999877810478
Regular Q-learning,50,713,0.035999998450279236
Regular Q-learning,50,714,0.027000000700354576
Regular Q-learning,50,715,0.0430000014603138
Regular Q-learning,50,716,0.03400000184774399
Regular Q-learning,50,717,0.035999998450279236
Regular Q-learning,50,718,0.028999999165534973
Regular Q-learning,50,719,0.04500000178813934
Regular Q-learning,50,720,0.03500000014901161
Regular Q-learning,50,721,0.03500000014901161
Regular Q-learning,50,722,0.02800000086426735
Regular Q-learning,50,723,0.04500000178813934
Regular Q-learning,50,724,0.035999998450279236
Regular Q-learning,50,725,0.03700000047683716
Regular Q-learning,50,726,0.027000000700354576
Regular Q-learning,50,727,0.04399999976158142
Regular Q-learning,50,728,0.035999998450279236
Regular Q-learning,50,729,0.035999998450279236
Regular Q-learning,50,730,0.027000000700354576
Regular Q-learning,50,731,0.041999999433755875
Regular Q-learning,50,732,0.035999998450279236
Regular Q-learning,50,733,0.03500000014901161
Regular Q-learning,50,734,0.03099999949336052
Regular Q-learning,50,735,0.0430000014603138
Regular Q-learning,50,736,0.03200000151991844
Regular Q-learning,50,737,0.03400000184774399
Regular Q-learning,50,738,0.032999999821186066
Regular Q-learning,50,739,0.0430000014603138
Regular Q-learning,50,740,0.03500000014901161
Regular Q-learning,50,741,0.03400000184774399
Regular Q-learning,50,742,0.03099999949336052
Regular Q-learning,50,743,0.04600000008940697
Regular Q-learning,50,744,0.03500000014901161
Regular Q-learning,50,745,0.03500000014901161
Regular Q-learning,50,746,0.02800000086426735
Regular Q-learning,50,747,0.0430000014603138
Regular Q-learning,50,748,0.03400000184774399
Regular Q-learning,50,749,0.032999999821186066
Regular Q-learning,50,750,0.02800000086426735
Regular Q-learning,50,751,0.04399999976158142
Regular Q-learning,50,752,0.032999999821186066
Regular Q-learning,50,753,0.03400000184774399
Regular Q-learning,50,754,0.02800000086426735
Regular Q-learning,50,755,0.041999999433755875
Regular Q-learning,50,756,0.03200000151991844
Regular Q-learning,50,757,0.03500000014901161
Regular Q-learning,50,758,0.02800000086426735
Regular Q-learning,50,759,0.0430000014603138
Regular Q-learning,50,760,0.03400000184774399
Regular Q-learning,50,761,0.03500000014901161
Regular Q-learning,50,762,0.027000000700354576
Regular Q-learning,50,763,0.041999999433755875
Regular Q-learning,50,764,0.035999998450279236
Regular Q-learning,50,765,0.032999999821186066
Regular Q-learning,50,766,0.028999999165534973
Regular Q-learning,50,767,0.041999999433755875
Regular Q-learning,50,768,0.03400000184774399
Regular Q-learning,50,769,0.032999999821186066
Regular Q-learning,50,770,0.027000000700354576
Regular Q-learning,50,771,0.039000000804662704
Regular Q-learning,50,772,0.029999999329447746
Regular Q-learning,50,773,0.035999998450279236
Regular Q-learning,50,774,0.032999999821186066
Regular Q-learning,50,775,0.04100000113248825
Regular Q-learning,50,776,0.03099999949336052
Regular Q-learning,50,777,0.03400000184774399
Regular Q-learning,50,778,0.032999999821186066
Regular Q-learning,50,779,0.041999999433755875
Regular Q-learning,50,780,0.03099999949336052
Regular Q-learning,50,781,0.03400000184774399
Regular Q-learning,50,782,0.029999999329447746
Regular Q-learning,50,783,0.041999999433755875
Regular Q-learning,50,784,0.03200000151991844
Regular Q-learning,50,785,0.03500000014901161
Regular Q-learning,50,786,0.03200000151991844
Regular Q-learning,50,787,0.0430000014603138
Regular Q-learning,50,788,0.029999999329447746
Regular Q-learning,50,789,0.03500000014901161
Regular Q-learning,50,790,0.029999999329447746
Regular Q-learning,50,791,0.041999999433755875
Regular Q-learning,50,792,0.032999999821186066
Regular Q-learning,50,793,0.032999999821186066
Regular Q-learning,50,794,0.026000000536441803
Regular Q-learning,50,795,0.0430000014603138
Regular Q-learning,50,796,0.029999999329447746
Regular Q-learning,50,797,0.035999998450279236
Regular Q-learning,50,798,0.03099999949336052
Regular Q-learning,50,799,0.03799999877810478
Regular Q-learning,50,800,0.03200000151991844
Regular Q-learning,50,801,0.035999998450279236
Regular Q-learning,50,802,0.02800000086426735
Regular Q-learning,50,803,0.041999999433755875
Regular Q-learning,50,804,0.028999999165534973
Regular Q-learning,50,805,0.032999999821186066
Regular Q-learning,50,806,0.02800000086426735
Regular Q-learning,50,807,0.04399999976158142
Regular Q-learning,50,808,0.028999999165534973
Regular Q-learning,50,809,0.032999999821186066
Regular Q-learning,50,810,0.03099999949336052
Regular Q-learning,50,811,0.041999999433755875
Regular Q-learning,50,812,0.029999999329447746
Regular Q-learning,50,813,0.03500000014901161
Regular Q-learning,50,814,0.029999999329447746
Regular Q-learning,50,815,0.039000000804662704
Regular Q-learning,50,816,0.03099999949336052
Regular Q-learning,50,817,0.03500000014901161
Regular Q-learning,50,818,0.03099999949336052
Regular Q-learning,50,819,0.03999999910593033
Regular Q-learning,50,820,0.029999999329447746
Regular Q-learning,50,821,0.03500000014901161
Regular Q-learning,50,822,0.029999999329447746
Regular Q-learning,50,823,0.0430000014603138
Regular Q-learning,50,824,0.02800000086426735
Regular Q-learning,50,825,0.03200000151991844
Regular Q-learning,50,826,0.028999999165534973
Regular Q-learning,50,827,0.04600000008940697
Regular Q-learning,50,828,0.027000000700354576
Regular Q-learning,50,829,0.03500000014901161
Regular Q-learning,50,830,0.029999999329447746
Regular Q-learning,50,831,0.04500000178813934
Regular Q-learning,50,832,0.028999999165534973
Regular Q-learning,50,833,0.03099999949336052
Regular Q-learning,50,834,0.032999999821186066
Regular Q-learning,50,835,0.04399999976158142
Regular Q-learning,50,836,0.028999999165534973
Regular Q-learning,50,837,0.028999999165534973
Regular Q-learning,50,838,0.03200000151991844
Regular Q-learning,50,839,0.04500000178813934
Regular Q-learning,50,840,0.03099999949336052
Regular Q-learning,50,841,0.029999999329447746
Regular Q-learning,50,842,0.03200000151991844
Regular Q-learning,50,843,0.04500000178813934
Regular Q-learning,50,844,0.03200000151991844
Regular Q-learning,50,845,0.02800000086426735
Regular Q-learning,50,846,0.03400000184774399
Regular Q-learning,50,847,0.04399999976158142
Regular Q-learning,50,848,0.029999999329447746
Regular Q-learning,50,849,0.028999999165534973
Regular Q-learning,50,850,0.03400000184774399
Regular Q-learning,50,851,0.04399999976158142
Regular Q-learning,50,852,0.028999999165534973
Regular Q-learning,50,853,0.028999999165534973
Regular Q-learning,50,854,0.03400000184774399
Regular Q-learning,50,855,0.04399999976158142
Regular Q-learning,50,856,0.028999999165534973
Regular Q-learning,50,857,0.02800000086426735
Regular Q-learning,50,858,0.035999998450279236
Regular Q-learning,50,859,0.04399999976158142
Regular Q-learning,50,860,0.03099999949336052
Regular Q-learning,50,861,0.029999999329447746
Regular Q-learning,50,862,0.03500000014901161
Regular Q-learning,50,863,0.041999999433755875
Regular Q-learning,50,864,0.032999999821186066
Regular Q-learning,50,865,0.02800000086426735
Regular Q-learning,50,866,0.035999998450279236
Regular Q-learning,50,867,0.041999999433755875
Regular Q-learning,50,868,0.029999999329447746
Regular Q-learning,50,869,0.028999999165534973
Regular Q-learning,50,870,0.03500000014901161
Regular Q-learning,50,871,0.04100000113248825
Regular Q-learning,50,872,0.028999999165534973
Regular Q-learning,50,873,0.028999999165534973
Regular Q-learning,50,874,0.035999998450279236
Regular Q-learning,50,875,0.041999999433755875
Regular Q-learning,50,876,0.028999999165534973
Regular Q-learning,50,877,0.029999999329447746
Regular Q-learning,50,878,0.03500000014901161
Regular Q-learning,50,879,0.04399999976158142
Regular Q-learning,50,880,0.027000000700354576
Regular Q-learning,50,881,0.03099999949336052
Regular Q-learning,50,882,0.032999999821186066
Regular Q-learning,50,883,0.04600000008940697
Regular Q-learning,50,884,0.02800000086426735
Regular Q-learning,50,885,0.028999999165534973
Regular Q-learning,50,886,0.03799999877810478
Regular Q-learning,50,887,0.04100000113248825
Regular Q-learning,50,888,0.02199999988079071
Regular Q-learning,50,889,0.03500000014901161
Regular Q-learning,50,890,0.03700000047683716
Regular Q-learning,50,891,0.039000000804662704
Regular Q-learning,50,892,0.02800000086426735
Regular Q-learning,50,893,0.03799999877810478
Regular Q-learning,50,894,0.032999999821186066
Regular Q-learning,50,895,0.039000000804662704
Regular Q-learning,50,896,0.029999999329447746
Regular Q-learning,50,897,0.03400000184774399
Regular Q-learning,50,898,0.03099999949336052
Regular Q-learning,50,899,0.03700000047683716
Regular Q-learning,50,900,0.02800000086426735
Regular Q-learning,50,901,0.03500000014901161
Regular Q-learning,50,902,0.03500000014901161
Regular Q-learning,50,903,0.04100000113248825
Regular Q-learning,50,904,0.028999999165534973
Regular Q-learning,50,905,0.035999998450279236
Regular Q-learning,50,906,0.03099999949336052
Regular Q-learning,50,907,0.03999999910593033
Regular Q-learning,50,908,0.03099999949336052
Regular Q-learning,50,909,0.03700000047683716
Regular Q-learning,50,910,0.03200000151991844
Regular Q-learning,50,911,0.035999998450279236
Regular Q-learning,50,912,0.02800000086426735
Regular Q-learning,50,913,0.03700000047683716
Regular Q-learning,50,914,0.03500000014901161
Regular Q-learning,50,915,0.03400000184774399
Regular Q-learning,50,916,0.02800000086426735
Regular Q-learning,50,917,0.03799999877810478
Regular Q-learning,50,918,0.03500000014901161
Regular Q-learning,50,919,0.035999998450279236
Regular Q-learning,50,920,0.02800000086426735
Regular Q-learning,50,921,0.03700000047683716
Regular Q-learning,50,922,0.03500000014901161
Regular Q-learning,50,923,0.03700000047683716
Regular Q-learning,50,924,0.027000000700354576
Regular Q-learning,50,925,0.03700000047683716
Regular Q-learning,50,926,0.03500000014901161
Regular Q-learning,50,927,0.03700000047683716
Regular Q-learning,50,928,0.027000000700354576
Regular Q-learning,50,929,0.03799999877810478
Regular Q-learning,50,930,0.03400000184774399
Regular Q-learning,50,931,0.035999998450279236
Regular Q-learning,50,932,0.026000000536441803
Regular Q-learning,50,933,0.03500000014901161
Regular Q-learning,50,934,0.035999998450279236
Regular Q-learning,50,935,0.03999999910593033
Regular Q-learning,50,936,0.020999999716877937
Regular Q-learning,50,937,0.03500000014901161
Regular Q-learning,50,938,0.035999998450279236
Regular Q-learning,50,939,0.03799999877810478
Regular Q-learning,50,940,0.023000000044703484
Regular Q-learning,50,941,0.03500000014901161
Regular Q-learning,50,942,0.03799999877810478
Regular Q-learning,50,943,0.039000000804662704
Regular Q-learning,50,944,0.023000000044703484
Regular Q-learning,50,945,0.03500000014901161
Regular Q-learning,50,946,0.03700000047683716
Regular Q-learning,50,947,0.039000000804662704
Regular Q-learning,50,948,0.024000000208616257
Regular Q-learning,50,949,0.032999999821186066
Regular Q-learning,50,950,0.03700000047683716
Regular Q-learning,50,951,0.039000000804662704
Regular Q-learning,50,952,0.024000000208616257
Regular Q-learning,50,953,0.035999998450279236
Regular Q-learning,50,954,0.03799999877810478
Regular Q-learning,50,955,0.03700000047683716
Regular Q-learning,50,956,0.02199999988079071
Regular Q-learning,50,957,0.03700000047683716
Regular Q-learning,50,958,0.03999999910593033
Regular Q-learning,50,959,0.035999998450279236
Regular Q-learning,50,960,0.023000000044703484
Regular Q-learning,50,961,0.035999998450279236
Regular Q-learning,50,962,0.039000000804662704
Regular Q-learning,50,963,0.032999999821186066
Regular Q-learning,50,964,0.02199999988079071
Regular Q-learning,50,965,0.03700000047683716
Regular Q-learning,50,966,0.039000000804662704
Regular Q-learning,50,967,0.035999998450279236
Regular Q-learning,50,968,0.023000000044703484
Regular Q-learning,50,969,0.03700000047683716
Regular Q-learning,50,970,0.035999998450279236
Regular Q-learning,50,971,0.03500000014901161
Regular Q-learning,50,972,0.023000000044703484
Regular Q-learning,50,973,0.03799999877810478
Regular Q-learning,50,974,0.03500000014901161
Regular Q-learning,50,975,0.035999998450279236
Regular Q-learning,50,976,0.024000000208616257
Regular Q-learning,50,977,0.03700000047683716
Regular Q-learning,50,978,0.028999999165534973
Regular Q-learning,50,979,0.04100000113248825
Regular Q-learning,50,980,0.027000000700354576
Regular Q-learning,50,981,0.032999999821186066
Regular Q-learning,50,982,0.029999999329447746
Regular Q-learning,50,983,0.03999999910593033
Regular Q-learning,50,984,0.02800000086426735
Regular Q-learning,50,985,0.03099999949336052
Regular Q-learning,50,986,0.03500000014901161
Regular Q-learning,50,987,0.03700000047683716
Regular Q-learning,50,988,0.026000000536441803
Regular Q-learning,50,989,0.032999999821186066
Regular Q-learning,50,990,0.032999999821186066
Regular Q-learning,50,991,0.035999998450279236
Regular Q-learning,50,992,0.02500000037252903
Regular Q-learning,50,993,0.035999998450279236
Regular Q-learning,50,994,0.03200000151991844
Regular Q-learning,50,995,0.03500000014901161
Regular Q-learning,50,996,0.026000000536441803
Regular Q-learning,50,997,0.03500000014901161
Regular Q-learning,50,998,0.03200000151991844
Regular Q-learning,50,999,0.032999999821186066
Regular Q-learning,50,1000,0.02500000037252903
Regular Q-learning,100,1,0.2709999978542328
Regular Q-learning,100,2,0.2240000069141388
Regular Q-learning,100,3,0.16599999368190765
Regular Q-learning,100,4,0.16899999976158142
Regular Q-learning,100,5,0.14499999582767487
Regular Q-learning,100,6,0.13500000536441803
Regular Q-learning,100,7,0.12399999797344208
Regular Q-learning,100,8,0.14000000059604645
Regular Q-learning,100,9,0.12800000607967377
Regular Q-learning,100,10,0.13699999451637268
Regular Q-learning,100,11,0.1340000033378601
Regular Q-learning,100,12,0.14300000667572021
Regular Q-learning,100,13,0.1379999965429306
Regular Q-learning,100,14,0.14900000393390656
Regular Q-learning,100,15,0.13699999451637268
Regular Q-learning,100,16,0.13199999928474426
Regular Q-learning,100,17,0.11699999868869781
Regular Q-learning,100,18,0.12600000202655792
Regular Q-learning,100,19,0.13500000536441803
Regular Q-learning,100,20,0.12099999934434891
Regular Q-learning,100,21,0.12600000202655792
Regular Q-learning,100,22,0.12700000405311584
Regular Q-learning,100,23,0.12399999797344208
Regular Q-learning,100,24,0.11800000071525574
Regular Q-learning,100,25,0.10700000077486038
Regular Q-learning,100,26,0.11800000071525574
Regular Q-learning,100,27,0.1120000034570694
Regular Q-learning,100,28,0.12200000137090683
Regular Q-learning,100,29,0.0989999994635582
Regular Q-learning,100,30,0.11299999803304672
Regular Q-learning,100,31,0.10100000351667404
Regular Q-learning,100,32,0.12300000339746475
Regular Q-learning,100,33,0.09099999815225601
Regular Q-learning,100,34,0.11500000208616257
Regular Q-learning,100,35,0.0949999988079071
Regular Q-learning,100,36,0.10499999672174454
Regular Q-learning,100,37,0.08799999952316284
Regular Q-learning,100,38,0.10100000351667404
Regular Q-learning,100,39,0.08900000154972076
Regular Q-learning,100,40,0.08699999749660492
Regular Q-learning,100,41,0.07699999958276749
Regular Q-learning,100,42,0.0820000022649765
Regular Q-learning,100,43,0.0820000022649765
Regular Q-learning,100,44,0.07800000160932541
Regular Q-learning,100,45,0.0820000022649765
Regular Q-learning,100,46,0.07699999958276749
Regular Q-learning,100,47,0.06800000369548798
Regular Q-learning,100,48,0.07999999821186066
Regular Q-learning,100,49,0.07400000095367432
Regular Q-learning,100,50,0.06800000369548798
Regular Q-learning,100,51,0.08399999886751175
Regular Q-learning,100,52,0.07500000298023224
Regular Q-learning,100,53,0.0689999982714653
Regular Q-learning,100,54,0.07599999755620956
Regular Q-learning,100,55,0.07599999755620956
Regular Q-learning,100,56,0.07000000029802322
Regular Q-learning,100,57,0.07100000232458115
Regular Q-learning,100,58,0.061000000685453415
Regular Q-learning,100,59,0.0689999982714653
Regular Q-learning,100,60,0.06300000101327896
Regular Q-learning,100,61,0.07000000029802322
Regular Q-learning,100,62,0.05700000002980232
Regular Q-learning,100,63,0.06800000369548798
Regular Q-learning,100,64,0.06199999898672104
Regular Q-learning,100,65,0.06800000369548798
Regular Q-learning,100,66,0.05900000035762787
Regular Q-learning,100,67,0.06800000369548798
Regular Q-learning,100,68,0.05900000035762787
Regular Q-learning,100,69,0.06499999761581421
Regular Q-learning,100,70,0.05900000035762787
Regular Q-learning,100,71,0.07199999690055847
Regular Q-learning,100,72,0.05999999865889549
Regular Q-learning,100,73,0.06599999964237213
Regular Q-learning,100,74,0.05900000035762787
Regular Q-learning,100,75,0.06300000101327896
Regular Q-learning,100,76,0.05700000002980232
Regular Q-learning,100,77,0.05999999865889549
Regular Q-learning,100,78,0.06199999898672104
Regular Q-learning,100,79,0.06400000303983688
Regular Q-learning,100,80,0.05700000002980232
Regular Q-learning,100,81,0.06599999964237213
Regular Q-learning,100,82,0.05299999937415123
Regular Q-learning,100,83,0.06199999898672104
Regular Q-learning,100,84,0.061000000685453415
Regular Q-learning,100,85,0.061000000685453415
Regular Q-learning,100,86,0.057999998331069946
Regular Q-learning,100,87,0.05900000035762787
Regular Q-learning,100,88,0.05900000035762787
Regular Q-learning,100,89,0.05900000035762787
Regular Q-learning,100,90,0.05400000140070915
Regular Q-learning,100,91,0.061000000685453415
Regular Q-learning,100,92,0.05900000035762787
Regular Q-learning,100,93,0.06300000101327896
Regular Q-learning,100,94,0.05700000002980232
Regular Q-learning,100,95,0.052000001072883606
Regular Q-learning,100,96,0.061000000685453415
Regular Q-learning,100,97,0.05999999865889549
Regular Q-learning,100,98,0.05700000002980232
Regular Q-learning,100,99,0.054999999701976776
Regular Q-learning,100,100,0.0560000017285347
Regular Q-learning,100,101,0.05700000002980232
Regular Q-learning,100,102,0.057999998331069946
Regular Q-learning,100,103,0.05900000035762787
Regular Q-learning,100,104,0.04899999871850014
Regular Q-learning,100,105,0.06300000101327896
Regular Q-learning,100,106,0.057999998331069946
Regular Q-learning,100,107,0.05400000140070915
Regular Q-learning,100,108,0.04800000041723251
Regular Q-learning,100,109,0.054999999701976776
Regular Q-learning,100,110,0.05400000140070915
Regular Q-learning,100,111,0.0560000017285347
Regular Q-learning,100,112,0.052000001072883606
Regular Q-learning,100,113,0.05900000035762787
Regular Q-learning,100,114,0.05400000140070915
Regular Q-learning,100,115,0.05700000002980232
Regular Q-learning,100,116,0.05700000002980232
Regular Q-learning,100,117,0.052000001072883606
Regular Q-learning,100,118,0.05000000074505806
Regular Q-learning,100,119,0.0560000017285347
Regular Q-learning,100,120,0.04899999871850014
Regular Q-learning,100,121,0.0560000017285347
Regular Q-learning,100,122,0.04800000041723251
Regular Q-learning,100,123,0.054999999701976776
Regular Q-learning,100,124,0.052000001072883606
Regular Q-learning,100,125,0.052000001072883606
Regular Q-learning,100,126,0.04800000041723251
Regular Q-learning,100,127,0.052000001072883606
Regular Q-learning,100,128,0.050999999046325684
Regular Q-learning,100,129,0.052000001072883606
Regular Q-learning,100,130,0.050999999046325684
Regular Q-learning,100,131,0.05400000140070915
Regular Q-learning,100,132,0.04399999976158142
Regular Q-learning,100,133,0.052000001072883606
Regular Q-learning,100,134,0.054999999701976776
Regular Q-learning,100,135,0.05299999937415123
Regular Q-learning,100,136,0.04800000041723251
Regular Q-learning,100,137,0.05400000140070915
Regular Q-learning,100,138,0.052000001072883606
Regular Q-learning,100,139,0.05000000074505806
Regular Q-learning,100,140,0.04699999839067459
Regular Q-learning,100,141,0.05400000140070915
Regular Q-learning,100,142,0.04800000041723251
Regular Q-learning,100,143,0.05299999937415123
Regular Q-learning,100,144,0.052000001072883606
Regular Q-learning,100,145,0.05299999937415123
Regular Q-learning,100,146,0.050999999046325684
Regular Q-learning,100,147,0.052000001072883606
Regular Q-learning,100,148,0.04800000041723251
Regular Q-learning,100,149,0.05299999937415123
Regular Q-learning,100,150,0.04899999871850014
Regular Q-learning,100,151,0.050999999046325684
Regular Q-learning,100,152,0.04699999839067459
Regular Q-learning,100,153,0.052000001072883606
Regular Q-learning,100,154,0.04899999871850014
Regular Q-learning,100,155,0.05299999937415123
Regular Q-learning,100,156,0.04899999871850014
Regular Q-learning,100,157,0.05000000074505806
Regular Q-learning,100,158,0.05000000074505806
Regular Q-learning,100,159,0.050999999046325684
Regular Q-learning,100,160,0.052000001072883606
Regular Q-learning,100,161,0.04699999839067459
Regular Q-learning,100,162,0.04800000041723251
Regular Q-learning,100,163,0.04699999839067459
Regular Q-learning,100,164,0.04800000041723251
Regular Q-learning,100,165,0.04399999976158142
Regular Q-learning,100,166,0.05400000140070915
Regular Q-learning,100,167,0.052000001072883606
Regular Q-learning,100,168,0.04399999976158142
Regular Q-learning,100,169,0.050999999046325684
Regular Q-learning,100,170,0.05299999937415123
Regular Q-learning,100,171,0.04399999976158142
Regular Q-learning,100,172,0.05000000074505806
Regular Q-learning,100,173,0.04699999839067459
Regular Q-learning,100,174,0.04800000041723251
Regular Q-learning,100,175,0.050999999046325684
Regular Q-learning,100,176,0.04899999871850014
Regular Q-learning,100,177,0.05000000074505806
Regular Q-learning,100,178,0.052000001072883606
Regular Q-learning,100,179,0.04500000178813934
Regular Q-learning,100,180,0.04800000041723251
Regular Q-learning,100,181,0.05000000074505806
Regular Q-learning,100,182,0.05299999937415123
Regular Q-learning,100,183,0.04899999871850014
Regular Q-learning,100,184,0.05000000074505806
Regular Q-learning,100,185,0.04699999839067459
Regular Q-learning,100,186,0.04699999839067459
Regular Q-learning,100,187,0.0430000014603138
Regular Q-learning,100,188,0.04500000178813934
Regular Q-learning,100,189,0.04399999976158142
Regular Q-learning,100,190,0.05000000074505806
Regular Q-learning,100,191,0.04800000041723251
Regular Q-learning,100,192,0.04399999976158142
Regular Q-learning,100,193,0.04399999976158142
Regular Q-learning,100,194,0.04500000178813934
Regular Q-learning,100,195,0.04500000178813934
Regular Q-learning,100,196,0.04899999871850014
Regular Q-learning,100,197,0.04699999839067459
Regular Q-learning,100,198,0.04399999976158142
Regular Q-learning,100,199,0.04399999976158142
Regular Q-learning,100,200,0.04800000041723251
Regular Q-learning,100,201,0.04500000178813934
Regular Q-learning,100,202,0.04600000008940697
Regular Q-learning,100,203,0.04699999839067459
Regular Q-learning,100,204,0.04699999839067459
Regular Q-learning,100,205,0.04899999871850014
Regular Q-learning,100,206,0.04600000008940697
Regular Q-learning,100,207,0.04800000041723251
Regular Q-learning,100,208,0.0430000014603138
Regular Q-learning,100,209,0.04500000178813934
Regular Q-learning,100,210,0.04800000041723251
Regular Q-learning,100,211,0.04399999976158142
Regular Q-learning,100,212,0.0430000014603138
Regular Q-learning,100,213,0.04699999839067459
Regular Q-learning,100,214,0.04600000008940697
Regular Q-learning,100,215,0.04600000008940697
Regular Q-learning,100,216,0.04500000178813934
Regular Q-learning,100,217,0.041999999433755875
Regular Q-learning,100,218,0.04699999839067459
Regular Q-learning,100,219,0.05000000074505806
Regular Q-learning,100,220,0.041999999433755875
Regular Q-learning,100,221,0.04600000008940697
Regular Q-learning,100,222,0.04399999976158142
Regular Q-learning,100,223,0.052000001072883606
Regular Q-learning,100,224,0.04399999976158142
Regular Q-learning,100,225,0.041999999433755875
Regular Q-learning,100,226,0.04800000041723251
Regular Q-learning,100,227,0.05000000074505806
Regular Q-learning,100,228,0.05000000074505806
Regular Q-learning,100,229,0.04500000178813934
Regular Q-learning,100,230,0.04600000008940697
Regular Q-learning,100,231,0.05000000074505806
Regular Q-learning,100,232,0.041999999433755875
Regular Q-learning,100,233,0.0430000014603138
Regular Q-learning,100,234,0.04399999976158142
Regular Q-learning,100,235,0.04800000041723251
Regular Q-learning,100,236,0.04399999976158142
Regular Q-learning,100,237,0.04899999871850014
Regular Q-learning,100,238,0.05000000074505806
Regular Q-learning,100,239,0.04699999839067459
Regular Q-learning,100,240,0.0430000014603138
Regular Q-learning,100,241,0.041999999433755875
Regular Q-learning,100,242,0.04699999839067459
Regular Q-learning,100,243,0.05000000074505806
Regular Q-learning,100,244,0.041999999433755875
Regular Q-learning,100,245,0.04600000008940697
Regular Q-learning,100,246,0.04600000008940697
Regular Q-learning,100,247,0.05000000074505806
Regular Q-learning,100,248,0.04399999976158142
Regular Q-learning,100,249,0.0430000014603138
Regular Q-learning,100,250,0.04800000041723251
Regular Q-learning,100,251,0.050999999046325684
Regular Q-learning,100,252,0.04399999976158142
Regular Q-learning,100,253,0.0430000014603138
Regular Q-learning,100,254,0.04399999976158142
Regular Q-learning,100,255,0.050999999046325684
Regular Q-learning,100,256,0.04399999976158142
Regular Q-learning,100,257,0.04600000008940697
Regular Q-learning,100,258,0.04899999871850014
Regular Q-learning,100,259,0.04899999871850014
Regular Q-learning,100,260,0.04500000178813934
Regular Q-learning,100,261,0.04399999976158142
Regular Q-learning,100,262,0.04699999839067459
Regular Q-learning,100,263,0.04699999839067459
Regular Q-learning,100,264,0.04399999976158142
Regular Q-learning,100,265,0.0430000014603138
Regular Q-learning,100,266,0.04899999871850014
Regular Q-learning,100,267,0.0430000014603138
Regular Q-learning,100,268,0.04800000041723251
Regular Q-learning,100,269,0.04500000178813934
Regular Q-learning,100,270,0.04800000041723251
Regular Q-learning,100,271,0.04600000008940697
Regular Q-learning,100,272,0.04600000008940697
Regular Q-learning,100,273,0.039000000804662704
Regular Q-learning,100,274,0.04600000008940697
Regular Q-learning,100,275,0.04399999976158142
Regular Q-learning,100,276,0.04500000178813934
Regular Q-learning,100,277,0.03799999877810478
Regular Q-learning,100,278,0.04699999839067459
Regular Q-learning,100,279,0.04899999871850014
Regular Q-learning,100,280,0.04500000178813934
Regular Q-learning,100,281,0.03799999877810478
Regular Q-learning,100,282,0.050999999046325684
Regular Q-learning,100,283,0.04600000008940697
Regular Q-learning,100,284,0.050999999046325684
Regular Q-learning,100,285,0.03700000047683716
Regular Q-learning,100,286,0.05000000074505806
Regular Q-learning,100,287,0.04500000178813934
Regular Q-learning,100,288,0.04100000113248825
Regular Q-learning,100,289,0.03500000014901161
Regular Q-learning,100,290,0.050999999046325684
Regular Q-learning,100,291,0.0430000014603138
Regular Q-learning,100,292,0.04500000178813934
Regular Q-learning,100,293,0.03400000184774399
Regular Q-learning,100,294,0.04899999871850014
Regular Q-learning,100,295,0.04399999976158142
Regular Q-learning,100,296,0.04100000113248825
Regular Q-learning,100,297,0.03500000014901161
Regular Q-learning,100,298,0.050999999046325684
Regular Q-learning,100,299,0.0430000014603138
Regular Q-learning,100,300,0.04100000113248825
Regular Q-learning,100,301,0.03799999877810478
Regular Q-learning,100,302,0.05000000074505806
Regular Q-learning,100,303,0.03999999910593033
Regular Q-learning,100,304,0.04100000113248825
Regular Q-learning,100,305,0.035999998450279236
Regular Q-learning,100,306,0.05299999937415123
Regular Q-learning,100,307,0.041999999433755875
Regular Q-learning,100,308,0.04500000178813934
Regular Q-learning,100,309,0.039000000804662704
Regular Q-learning,100,310,0.04399999976158142
Regular Q-learning,100,311,0.0430000014603138
Regular Q-learning,100,312,0.04399999976158142
Regular Q-learning,100,313,0.03999999910593033
Regular Q-learning,100,314,0.04399999976158142
Regular Q-learning,100,315,0.04100000113248825
Regular Q-learning,100,316,0.0430000014603138
Regular Q-learning,100,317,0.041999999433755875
Regular Q-learning,100,318,0.04699999839067459
Regular Q-learning,100,319,0.041999999433755875
Regular Q-learning,100,320,0.0430000014603138
Regular Q-learning,100,321,0.03700000047683716
Regular Q-learning,100,322,0.05299999937415123
Regular Q-learning,100,323,0.03999999910593033
Regular Q-learning,100,324,0.0430000014603138
Regular Q-learning,100,325,0.04100000113248825
Regular Q-learning,100,326,0.04600000008940697
Regular Q-learning,100,327,0.04100000113248825
Regular Q-learning,100,328,0.03999999910593033
Regular Q-learning,100,329,0.0430000014603138
Regular Q-learning,100,330,0.04399999976158142
Regular Q-learning,100,331,0.039000000804662704
Regular Q-learning,100,332,0.04399999976158142
Regular Q-learning,100,333,0.0430000014603138
Regular Q-learning,100,334,0.04500000178813934
Regular Q-learning,100,335,0.039000000804662704
Regular Q-learning,100,336,0.04399999976158142
Regular Q-learning,100,337,0.041999999433755875
Regular Q-learning,100,338,0.04899999871850014
Regular Q-learning,100,339,0.04100000113248825
Regular Q-learning,100,340,0.0430000014603138
Regular Q-learning,100,341,0.04500000178813934
Regular Q-learning,100,342,0.0430000014603138
Regular Q-learning,100,343,0.03799999877810478
Regular Q-learning,100,344,0.04699999839067459
Regular Q-learning,100,345,0.03999999910593033
Regular Q-learning,100,346,0.04500000178813934
Regular Q-learning,100,347,0.04100000113248825
Regular Q-learning,100,348,0.041999999433755875
Regular Q-learning,100,349,0.041999999433755875
Regular Q-learning,100,350,0.04500000178813934
Regular Q-learning,100,351,0.03999999910593033
Regular Q-learning,100,352,0.04399999976158142
Regular Q-learning,100,353,0.04399999976158142
Regular Q-learning,100,354,0.0430000014603138
Regular Q-learning,100,355,0.04600000008940697
Regular Q-learning,100,356,0.03999999910593033
Regular Q-learning,100,357,0.041999999433755875
Regular Q-learning,100,358,0.04399999976158142
Regular Q-learning,100,359,0.0430000014603138
Regular Q-learning,100,360,0.035999998450279236
Regular Q-learning,100,361,0.04399999976158142
Regular Q-learning,100,362,0.04600000008940697
Regular Q-learning,100,363,0.03999999910593033
Regular Q-learning,100,364,0.03999999910593033
Regular Q-learning,100,365,0.0430000014603138
Regular Q-learning,100,366,0.04600000008940697
Regular Q-learning,100,367,0.03700000047683716
Regular Q-learning,100,368,0.0430000014603138
Regular Q-learning,100,369,0.041999999433755875
Regular Q-learning,100,370,0.04600000008940697
Regular Q-learning,100,371,0.04100000113248825
Regular Q-learning,100,372,0.041999999433755875
Regular Q-learning,100,373,0.04100000113248825
Regular Q-learning,100,374,0.04500000178813934
Regular Q-learning,100,375,0.03799999877810478
Regular Q-learning,100,376,0.04100000113248825
Regular Q-learning,100,377,0.04399999976158142
Regular Q-learning,100,378,0.04600000008940697
Regular Q-learning,100,379,0.04100000113248825
Regular Q-learning,100,380,0.03999999910593033
Regular Q-learning,100,381,0.04100000113248825
Regular Q-learning,100,382,0.04600000008940697
Regular Q-learning,100,383,0.0430000014603138
Regular Q-learning,100,384,0.04100000113248825
Regular Q-learning,100,385,0.039000000804662704
Regular Q-learning,100,386,0.04500000178813934
Regular Q-learning,100,387,0.041999999433755875
Regular Q-learning,100,388,0.0430000014603138
Regular Q-learning,100,389,0.041999999433755875
Regular Q-learning,100,390,0.04500000178813934
Regular Q-learning,100,391,0.04399999976158142
Regular Q-learning,100,392,0.04399999976158142
Regular Q-learning,100,393,0.039000000804662704
Regular Q-learning,100,394,0.039000000804662704
Regular Q-learning,100,395,0.04399999976158142
Regular Q-learning,100,396,0.0430000014603138
Regular Q-learning,100,397,0.041999999433755875
Regular Q-learning,100,398,0.0430000014603138
Regular Q-learning,100,399,0.0430000014603138
Regular Q-learning,100,400,0.04100000113248825
Regular Q-learning,100,401,0.04600000008940697
Regular Q-learning,100,402,0.03999999910593033
Regular Q-learning,100,403,0.04399999976158142
Regular Q-learning,100,404,0.04399999976158142
Regular Q-learning,100,405,0.04100000113248825
Regular Q-learning,100,406,0.039000000804662704
Regular Q-learning,100,407,0.04500000178813934
Regular Q-learning,100,408,0.04399999976158142
Regular Q-learning,100,409,0.04100000113248825
Regular Q-learning,100,410,0.03799999877810478
Regular Q-learning,100,411,0.04500000178813934
Regular Q-learning,100,412,0.04500000178813934
Regular Q-learning,100,413,0.04100000113248825
Regular Q-learning,100,414,0.039000000804662704
Regular Q-learning,100,415,0.04800000041723251
Regular Q-learning,100,416,0.04100000113248825
Regular Q-learning,100,417,0.04500000178813934
Regular Q-learning,100,418,0.04100000113248825
Regular Q-learning,100,419,0.04500000178813934
Regular Q-learning,100,420,0.041999999433755875
Regular Q-learning,100,421,0.04699999839067459
Regular Q-learning,100,422,0.03799999877810478
Regular Q-learning,100,423,0.0430000014603138
Regular Q-learning,100,424,0.0430000014603138
Regular Q-learning,100,425,0.0430000014603138
Regular Q-learning,100,426,0.03799999877810478
Regular Q-learning,100,427,0.04500000178813934
Regular Q-learning,100,428,0.04500000178813934
Regular Q-learning,100,429,0.0430000014603138
Regular Q-learning,100,430,0.03700000047683716
Regular Q-learning,100,431,0.04399999976158142
Regular Q-learning,100,432,0.04600000008940697
Regular Q-learning,100,433,0.03999999910593033
Regular Q-learning,100,434,0.03799999877810478
Regular Q-learning,100,435,0.0430000014603138
Regular Q-learning,100,436,0.04399999976158142
Regular Q-learning,100,437,0.041999999433755875
Regular Q-learning,100,438,0.041999999433755875
Regular Q-learning,100,439,0.04100000113248825
Regular Q-learning,100,440,0.04100000113248825
Regular Q-learning,100,441,0.04100000113248825
Regular Q-learning,100,442,0.041999999433755875
Regular Q-learning,100,443,0.03999999910593033
Regular Q-learning,100,444,0.0430000014603138
Regular Q-learning,100,445,0.04399999976158142
Regular Q-learning,100,446,0.04100000113248825
Regular Q-learning,100,447,0.04399999976158142
Regular Q-learning,100,448,0.03799999877810478
Regular Q-learning,100,449,0.04399999976158142
Regular Q-learning,100,450,0.041999999433755875
Regular Q-learning,100,451,0.04100000113248825
Regular Q-learning,100,452,0.04100000113248825
Regular Q-learning,100,453,0.04399999976158142
Regular Q-learning,100,454,0.0430000014603138
Regular Q-learning,100,455,0.04399999976158142
Regular Q-learning,100,456,0.03799999877810478
Regular Q-learning,100,457,0.04100000113248825
Regular Q-learning,100,458,0.04399999976158142
Regular Q-learning,100,459,0.04500000178813934
Regular Q-learning,100,460,0.03999999910593033
Regular Q-learning,100,461,0.03999999910593033
Regular Q-learning,100,462,0.04100000113248825
Regular Q-learning,100,463,0.04500000178813934
Regular Q-learning,100,464,0.04100000113248825
Regular Q-learning,100,465,0.039000000804662704
Regular Q-learning,100,466,0.041999999433755875
Regular Q-learning,100,467,0.04399999976158142
Regular Q-learning,100,468,0.03700000047683716
Regular Q-learning,100,469,0.0430000014603138
Regular Q-learning,100,470,0.04699999839067459
Regular Q-learning,100,471,0.04600000008940697
Regular Q-learning,100,472,0.03400000184774399
Regular Q-learning,100,473,0.0430000014603138
Regular Q-learning,100,474,0.04100000113248825
Regular Q-learning,100,475,0.04600000008940697
Regular Q-learning,100,476,0.03700000047683716
Regular Q-learning,100,477,0.04699999839067459
Regular Q-learning,100,478,0.039000000804662704
Regular Q-learning,100,479,0.04500000178813934
Regular Q-learning,100,480,0.041999999433755875
Regular Q-learning,100,481,0.03799999877810478
Regular Q-learning,100,482,0.039000000804662704
Regular Q-learning,100,483,0.04800000041723251
Regular Q-learning,100,484,0.04100000113248825
Regular Q-learning,100,485,0.03700000047683716
Regular Q-learning,100,486,0.0430000014603138
Regular Q-learning,100,487,0.04899999871850014
Regular Q-learning,100,488,0.03799999877810478
Regular Q-learning,100,489,0.04100000113248825
Regular Q-learning,100,490,0.041999999433755875
Regular Q-learning,100,491,0.0430000014603138
Regular Q-learning,100,492,0.039000000804662704
Regular Q-learning,100,493,0.04100000113248825
Regular Q-learning,100,494,0.04399999976158142
Regular Q-learning,100,495,0.04500000178813934
Regular Q-learning,100,496,0.03700000047683716
Regular Q-learning,100,497,0.041999999433755875
Regular Q-learning,100,498,0.04500000178813934
Regular Q-learning,100,499,0.04500000178813934
Regular Q-learning,100,500,0.03700000047683716
Regular Q-learning,100,501,0.041999999433755875
Regular Q-learning,100,502,0.03999999910593033
Regular Q-learning,100,503,0.04399999976158142
Regular Q-learning,100,504,0.041999999433755875
Regular Q-learning,100,505,0.0430000014603138
Regular Q-learning,100,506,0.04100000113248825
Regular Q-learning,100,507,0.03999999910593033
Regular Q-learning,100,508,0.04100000113248825
Regular Q-learning,100,509,0.04100000113248825
Regular Q-learning,100,510,0.039000000804662704
Regular Q-learning,100,511,0.0430000014603138
Regular Q-learning,100,512,0.0430000014603138
Regular Q-learning,100,513,0.039000000804662704
Regular Q-learning,100,514,0.04100000113248825
Regular Q-learning,100,515,0.04399999976158142
Regular Q-learning,100,516,0.041999999433755875
Regular Q-learning,100,517,0.041999999433755875
Regular Q-learning,100,518,0.041999999433755875
Regular Q-learning,100,519,0.0430000014603138
Regular Q-learning,100,520,0.041999999433755875
Regular Q-learning,100,521,0.035999998450279236
Regular Q-learning,100,522,0.04899999871850014
Regular Q-learning,100,523,0.04100000113248825
Regular Q-learning,100,524,0.035999998450279236
Regular Q-learning,100,525,0.03400000184774399
Regular Q-learning,100,526,0.04899999871850014
Regular Q-learning,100,527,0.04399999976158142
Regular Q-learning,100,528,0.03799999877810478
Regular Q-learning,100,529,0.035999998450279236
Regular Q-learning,100,530,0.04500000178813934
Regular Q-learning,100,531,0.04600000008940697
Regular Q-learning,100,532,0.039000000804662704
Regular Q-learning,100,533,0.03700000047683716
Regular Q-learning,100,534,0.05000000074505806
Regular Q-learning,100,535,0.04500000178813934
Regular Q-learning,100,536,0.04100000113248825
Regular Q-learning,100,537,0.03799999877810478
Regular Q-learning,100,538,0.04500000178813934
Regular Q-learning,100,539,0.04100000113248825
Regular Q-learning,100,540,0.04399999976158142
Regular Q-learning,100,541,0.035999998450279236
Regular Q-learning,100,542,0.04600000008940697
Regular Q-learning,100,543,0.03999999910593033
Regular Q-learning,100,544,0.04399999976158142
Regular Q-learning,100,545,0.03700000047683716
Regular Q-learning,100,546,0.04399999976158142
Regular Q-learning,100,547,0.04100000113248825
Regular Q-learning,100,548,0.04399999976158142
Regular Q-learning,100,549,0.03500000014901161
Regular Q-learning,100,550,0.04699999839067459
Regular Q-learning,100,551,0.03799999877810478
Regular Q-learning,100,552,0.0430000014603138
Regular Q-learning,100,553,0.03700000047683716
Regular Q-learning,100,554,0.04500000178813934
Regular Q-learning,100,555,0.03500000014901161
Regular Q-learning,100,556,0.04600000008940697
Regular Q-learning,100,557,0.035999998450279236
Regular Q-learning,100,558,0.04699999839067459
Regular Q-learning,100,559,0.03799999877810478
Regular Q-learning,100,560,0.0430000014603138
Regular Q-learning,100,561,0.03400000184774399
Regular Q-learning,100,562,0.04500000178813934
Regular Q-learning,100,563,0.035999998450279236
Regular Q-learning,100,564,0.04500000178813934
Regular Q-learning,100,565,0.03500000014901161
Regular Q-learning,100,566,0.04600000008940697
Regular Q-learning,100,567,0.039000000804662704
Regular Q-learning,100,568,0.04100000113248825
Regular Q-learning,100,569,0.03400000184774399
Regular Q-learning,100,570,0.04699999839067459
Regular Q-learning,100,571,0.041999999433755875
Regular Q-learning,100,572,0.039000000804662704
Regular Q-learning,100,573,0.035999998450279236
Regular Q-learning,100,574,0.0430000014603138
Regular Q-learning,100,575,0.04500000178813934
Regular Q-learning,100,576,0.03799999877810478
Regular Q-learning,100,577,0.035999998450279236
Regular Q-learning,100,578,0.0430000014603138
Regular Q-learning,100,579,0.04100000113248825
Regular Q-learning,100,580,0.03799999877810478
Regular Q-learning,100,581,0.035999998450279236
Regular Q-learning,100,582,0.04600000008940697
Regular Q-learning,100,583,0.039000000804662704
Regular Q-learning,100,584,0.035999998450279236
Regular Q-learning,100,585,0.03799999877810478
Regular Q-learning,100,586,0.04600000008940697
Regular Q-learning,100,587,0.03999999910593033
Regular Q-learning,100,588,0.03500000014901161
Regular Q-learning,100,589,0.039000000804662704
Regular Q-learning,100,590,0.04800000041723251
Regular Q-learning,100,591,0.03799999877810478
Regular Q-learning,100,592,0.03500000014901161
Regular Q-learning,100,593,0.03200000151991844
Regular Q-learning,100,594,0.04899999871850014
Regular Q-learning,100,595,0.041999999433755875
Regular Q-learning,100,596,0.03500000014901161
Regular Q-learning,100,597,0.03700000047683716
Regular Q-learning,100,598,0.050999999046325684
Regular Q-learning,100,599,0.039000000804662704
Regular Q-learning,100,600,0.03500000014901161
Regular Q-learning,100,601,0.03500000014901161
Regular Q-learning,100,602,0.04600000008940697
Regular Q-learning,100,603,0.04100000113248825
Regular Q-learning,100,604,0.03500000014901161
Regular Q-learning,100,605,0.03799999877810478
Regular Q-learning,100,606,0.04600000008940697
Regular Q-learning,100,607,0.041999999433755875
Regular Q-learning,100,608,0.039000000804662704
Regular Q-learning,100,609,0.035999998450279236
Regular Q-learning,100,610,0.041999999433755875
Regular Q-learning,100,611,0.04100000113248825
Regular Q-learning,100,612,0.03500000014901161
Regular Q-learning,100,613,0.035999998450279236
Regular Q-learning,100,614,0.0430000014603138
Regular Q-learning,100,615,0.04500000178813934
Regular Q-learning,100,616,0.03099999949336052
Regular Q-learning,100,617,0.03700000047683716
Regular Q-learning,100,618,0.04399999976158142
Regular Q-learning,100,619,0.04100000113248825
Regular Q-learning,100,620,0.03400000184774399
Regular Q-learning,100,621,0.03500000014901161
Regular Q-learning,100,622,0.04399999976158142
Regular Q-learning,100,623,0.041999999433755875
Regular Q-learning,100,624,0.03400000184774399
Regular Q-learning,100,625,0.03400000184774399
Regular Q-learning,100,626,0.04500000178813934
Regular Q-learning,100,627,0.03999999910593033
Regular Q-learning,100,628,0.03500000014901161
Regular Q-learning,100,629,0.03400000184774399
Regular Q-learning,100,630,0.04399999976158142
Regular Q-learning,100,631,0.039000000804662704
Regular Q-learning,100,632,0.03500000014901161
Regular Q-learning,100,633,0.03400000184774399
Regular Q-learning,100,634,0.04100000113248825
Regular Q-learning,100,635,0.04100000113248825
Regular Q-learning,100,636,0.03500000014901161
Regular Q-learning,100,637,0.03700000047683716
Regular Q-learning,100,638,0.041999999433755875
Regular Q-learning,100,639,0.03700000047683716
Regular Q-learning,100,640,0.03500000014901161
Regular Q-learning,100,641,0.039000000804662704
Regular Q-learning,100,642,0.0430000014603138
Regular Q-learning,100,643,0.03799999877810478
Regular Q-learning,100,644,0.03500000014901161
Regular Q-learning,100,645,0.03799999877810478
Regular Q-learning,100,646,0.041999999433755875
Regular Q-learning,100,647,0.03799999877810478
Regular Q-learning,100,648,0.03400000184774399
Regular Q-learning,100,649,0.039000000804662704
Regular Q-learning,100,650,0.041999999433755875
Regular Q-learning,100,651,0.03999999910593033
Regular Q-learning,100,652,0.03400000184774399
Regular Q-learning,100,653,0.03799999877810478
Regular Q-learning,100,654,0.0430000014603138
Regular Q-learning,100,655,0.03999999910593033
Regular Q-learning,100,656,0.03099999949336052
Regular Q-learning,100,657,0.03799999877810478
Regular Q-learning,100,658,0.04600000008940697
Regular Q-learning,100,659,0.03799999877810478
Regular Q-learning,100,660,0.03200000151991844
Regular Q-learning,100,661,0.03700000047683716
Regular Q-learning,100,662,0.041999999433755875
Regular Q-learning,100,663,0.03799999877810478
Regular Q-learning,100,664,0.03700000047683716
Regular Q-learning,100,665,0.03799999877810478
Regular Q-learning,100,666,0.041999999433755875
Regular Q-learning,100,667,0.03700000047683716
Regular Q-learning,100,668,0.039000000804662704
Regular Q-learning,100,669,0.035999998450279236
Regular Q-learning,100,670,0.041999999433755875
Regular Q-learning,100,671,0.035999998450279236
Regular Q-learning,100,672,0.039000000804662704
Regular Q-learning,100,673,0.03700000047683716
Regular Q-learning,100,674,0.03999999910593033
Regular Q-learning,100,675,0.04100000113248825
Regular Q-learning,100,676,0.03700000047683716
Regular Q-learning,100,677,0.03799999877810478
Regular Q-learning,100,678,0.03700000047683716
Regular Q-learning,100,679,0.03999999910593033
Regular Q-learning,100,680,0.03700000047683716
Regular Q-learning,100,681,0.041999999433755875
Regular Q-learning,100,682,0.035999998450279236
Regular Q-learning,100,683,0.03999999910593033
Regular Q-learning,100,684,0.035999998450279236
Regular Q-learning,100,685,0.04100000113248825
Regular Q-learning,100,686,0.035999998450279236
Regular Q-learning,100,687,0.041999999433755875
Regular Q-learning,100,688,0.039000000804662704
Regular Q-learning,100,689,0.03999999910593033
Regular Q-learning,100,690,0.032999999821186066
Regular Q-learning,100,691,0.041999999433755875
Regular Q-learning,100,692,0.039000000804662704
Regular Q-learning,100,693,0.039000000804662704
Regular Q-learning,100,694,0.035999998450279236
Regular Q-learning,100,695,0.0430000014603138
Regular Q-learning,100,696,0.03500000014901161
Regular Q-learning,100,697,0.039000000804662704
Regular Q-learning,100,698,0.03700000047683716
Regular Q-learning,100,699,0.04100000113248825
Regular Q-learning,100,700,0.039000000804662704
Regular Q-learning,100,701,0.03700000047683716
Regular Q-learning,100,702,0.039000000804662704
Regular Q-learning,100,703,0.04100000113248825
Regular Q-learning,100,704,0.03500000014901161
Regular Q-learning,100,705,0.03700000047683716
Regular Q-learning,100,706,0.03999999910593033
Regular Q-learning,100,707,0.041999999433755875
Regular Q-learning,100,708,0.039000000804662704
Regular Q-learning,100,709,0.03400000184774399
Regular Q-learning,100,710,0.04100000113248825
Regular Q-learning,100,711,0.03999999910593033
Regular Q-learning,100,712,0.039000000804662704
Regular Q-learning,100,713,0.03500000014901161
Regular Q-learning,100,714,0.039000000804662704
Regular Q-learning,100,715,0.041999999433755875
Regular Q-learning,100,716,0.03700000047683716
Regular Q-learning,100,717,0.03700000047683716
Regular Q-learning,100,718,0.035999998450279236
Regular Q-learning,100,719,0.04399999976158142
Regular Q-learning,100,720,0.03500000014901161
Regular Q-learning,100,721,0.04100000113248825
Regular Q-learning,100,722,0.03700000047683716
Regular Q-learning,100,723,0.03999999910593033
Regular Q-learning,100,724,0.039000000804662704
Regular Q-learning,100,725,0.04100000113248825
Regular Q-learning,100,726,0.03400000184774399
Regular Q-learning,100,727,0.03999999910593033
Regular Q-learning,100,728,0.03200000151991844
Regular Q-learning,100,729,0.041999999433755875
Regular Q-learning,100,730,0.03700000047683716
Regular Q-learning,100,731,0.03999999910593033
Regular Q-learning,100,732,0.03500000014901161
Regular Q-learning,100,733,0.04399999976158142
Regular Q-learning,100,734,0.03799999877810478
Regular Q-learning,100,735,0.03799999877810478
Regular Q-learning,100,736,0.035999998450279236
Regular Q-learning,100,737,0.04100000113248825
Regular Q-learning,100,738,0.035999998450279236
Regular Q-learning,100,739,0.03999999910593033
Regular Q-learning,100,740,0.03700000047683716
Regular Q-learning,100,741,0.041999999433755875
Regular Q-learning,100,742,0.03700000047683716
Regular Q-learning,100,743,0.039000000804662704
Regular Q-learning,100,744,0.03500000014901161
Regular Q-learning,100,745,0.03999999910593033
Regular Q-learning,100,746,0.03999999910593033
Regular Q-learning,100,747,0.03999999910593033
Regular Q-learning,100,748,0.035999998450279236
Regular Q-learning,100,749,0.039000000804662704
Regular Q-learning,100,750,0.03799999877810478
Regular Q-learning,100,751,0.04100000113248825
Regular Q-learning,100,752,0.03799999877810478
Regular Q-learning,100,753,0.03799999877810478
Regular Q-learning,100,754,0.03799999877810478
Regular Q-learning,100,755,0.0430000014603138
Regular Q-learning,100,756,0.035999998450279236
Regular Q-learning,100,757,0.035999998450279236
Regular Q-learning,100,758,0.03799999877810478
Regular Q-learning,100,759,0.041999999433755875
Regular Q-learning,100,760,0.03500000014901161
Regular Q-learning,100,761,0.035999998450279236
Regular Q-learning,100,762,0.04100000113248825
Regular Q-learning,100,763,0.041999999433755875
Regular Q-learning,100,764,0.035999998450279236
Regular Q-learning,100,765,0.03700000047683716
Regular Q-learning,100,766,0.04100000113248825
Regular Q-learning,100,767,0.041999999433755875
Regular Q-learning,100,768,0.03500000014901161
Regular Q-learning,100,769,0.03200000151991844
Regular Q-learning,100,770,0.03999999910593033
Regular Q-learning,100,771,0.041999999433755875
Regular Q-learning,100,772,0.035999998450279236
Regular Q-learning,100,773,0.03500000014901161
Regular Q-learning,100,774,0.0430000014603138
Regular Q-learning,100,775,0.03999999910593033
Regular Q-learning,100,776,0.03700000047683716
Regular Q-learning,100,777,0.03400000184774399
Regular Q-learning,100,778,0.04100000113248825
Regular Q-learning,100,779,0.041999999433755875
Regular Q-learning,100,780,0.03799999877810478
Regular Q-learning,100,781,0.032999999821186066
Regular Q-learning,100,782,0.039000000804662704
Regular Q-learning,100,783,0.0430000014603138
Regular Q-learning,100,784,0.03700000047683716
Regular Q-learning,100,785,0.03200000151991844
Regular Q-learning,100,786,0.03799999877810478
Regular Q-learning,100,787,0.04399999976158142
Regular Q-learning,100,788,0.041999999433755875
Regular Q-learning,100,789,0.03099999949336052
Regular Q-learning,100,790,0.03799999877810478
Regular Q-learning,100,791,0.0430000014603138
Regular Q-learning,100,792,0.03400000184774399
Regular Q-learning,100,793,0.03500000014901161
Regular Q-learning,100,794,0.0430000014603138
Regular Q-learning,100,795,0.04100000113248825
Regular Q-learning,100,796,0.03700000047683716
Regular Q-learning,100,797,0.03200000151991844
Regular Q-learning,100,798,0.03999999910593033
Regular Q-learning,100,799,0.04500000178813934
Regular Q-learning,100,800,0.03799999877810478
Regular Q-learning,100,801,0.03099999949336052
Regular Q-learning,100,802,0.03799999877810478
Regular Q-learning,100,803,0.04500000178813934
Regular Q-learning,100,804,0.03700000047683716
Regular Q-learning,100,805,0.03099999949336052
Regular Q-learning,100,806,0.039000000804662704
Regular Q-learning,100,807,0.04600000008940697
Regular Q-learning,100,808,0.03700000047683716
Regular Q-learning,100,809,0.03099999949336052
Regular Q-learning,100,810,0.041999999433755875
Regular Q-learning,100,811,0.0430000014603138
Regular Q-learning,100,812,0.039000000804662704
Regular Q-learning,100,813,0.027000000700354576
Regular Q-learning,100,814,0.03999999910593033
Regular Q-learning,100,815,0.04500000178813934
Regular Q-learning,100,816,0.03799999877810478
Regular Q-learning,100,817,0.03200000151991844
Regular Q-learning,100,818,0.03999999910593033
Regular Q-learning,100,819,0.04500000178813934
Regular Q-learning,100,820,0.03500000014901161
Regular Q-learning,100,821,0.02800000086426735
Regular Q-learning,100,822,0.039000000804662704
Regular Q-learning,100,823,0.04600000008940697
Regular Q-learning,100,824,0.039000000804662704
Regular Q-learning,100,825,0.02800000086426735
Regular Q-learning,100,826,0.039000000804662704
Regular Q-learning,100,827,0.04800000041723251
Regular Q-learning,100,828,0.03799999877810478
Regular Q-learning,100,829,0.029999999329447746
Regular Q-learning,100,830,0.039000000804662704
Regular Q-learning,100,831,0.04500000178813934
Regular Q-learning,100,832,0.035999998450279236
Regular Q-learning,100,833,0.029999999329447746
Regular Q-learning,100,834,0.03999999910593033
Regular Q-learning,100,835,0.04399999976158142
Regular Q-learning,100,836,0.03799999877810478
Regular Q-learning,100,837,0.029999999329447746
Regular Q-learning,100,838,0.03799999877810478
Regular Q-learning,100,839,0.04699999839067459
Regular Q-learning,100,840,0.03999999910593033
Regular Q-learning,100,841,0.02800000086426735
Regular Q-learning,100,842,0.03799999877810478
Regular Q-learning,100,843,0.04699999839067459
Regular Q-learning,100,844,0.03799999877810478
Regular Q-learning,100,845,0.029999999329447746
Regular Q-learning,100,846,0.032999999821186066
Regular Q-learning,100,847,0.04399999976158142
Regular Q-learning,100,848,0.041999999433755875
Regular Q-learning,100,849,0.03099999949336052
Regular Q-learning,100,850,0.03700000047683716
Regular Q-learning,100,851,0.041999999433755875
Regular Q-learning,100,852,0.03999999910593033
Regular Q-learning,100,853,0.03099999949336052
Regular Q-learning,100,854,0.03799999877810478
Regular Q-learning,100,855,0.04399999976158142
Regular Q-learning,100,856,0.04100000113248825
Regular Q-learning,100,857,0.03099999949336052
Regular Q-learning,100,858,0.03799999877810478
Regular Q-learning,100,859,0.04399999976158142
Regular Q-learning,100,860,0.039000000804662704
Regular Q-learning,100,861,0.032999999821186066
Regular Q-learning,100,862,0.039000000804662704
Regular Q-learning,100,863,0.04399999976158142
Regular Q-learning,100,864,0.039000000804662704
Regular Q-learning,100,865,0.02800000086426735
Regular Q-learning,100,866,0.04100000113248825
Regular Q-learning,100,867,0.04500000178813934
Regular Q-learning,100,868,0.039000000804662704
Regular Q-learning,100,869,0.028999999165534973
Regular Q-learning,100,870,0.04399999976158142
Regular Q-learning,100,871,0.041999999433755875
Regular Q-learning,100,872,0.03700000047683716
Regular Q-learning,100,873,0.03099999949336052
Regular Q-learning,100,874,0.0430000014603138
Regular Q-learning,100,875,0.041999999433755875
Regular Q-learning,100,876,0.039000000804662704
Regular Q-learning,100,877,0.028999999165534973
Regular Q-learning,100,878,0.041999999433755875
Regular Q-learning,100,879,0.04100000113248825
Regular Q-learning,100,880,0.03799999877810478
Regular Q-learning,100,881,0.03400000184774399
Regular Q-learning,100,882,0.039000000804662704
Regular Q-learning,100,883,0.041999999433755875
Regular Q-learning,100,884,0.039000000804662704
Regular Q-learning,100,885,0.028999999165534973
Regular Q-learning,100,886,0.041999999433755875
Regular Q-learning,100,887,0.03999999910593033
Regular Q-learning,100,888,0.03500000014901161
Regular Q-learning,100,889,0.035999998450279236
Regular Q-learning,100,890,0.03799999877810478
Regular Q-learning,100,891,0.03799999877810478
Regular Q-learning,100,892,0.03700000047683716
Regular Q-learning,100,893,0.039000000804662704
Regular Q-learning,100,894,0.03799999877810478
Regular Q-learning,100,895,0.03799999877810478
Regular Q-learning,100,896,0.03700000047683716
Regular Q-learning,100,897,0.03799999877810478
Regular Q-learning,100,898,0.03999999910593033
Regular Q-learning,100,899,0.03700000047683716
Regular Q-learning,100,900,0.03700000047683716
Regular Q-learning,100,901,0.035999998450279236
Regular Q-learning,100,902,0.03700000047683716
Regular Q-learning,100,903,0.03799999877810478
Regular Q-learning,100,904,0.03799999877810478
Regular Q-learning,100,905,0.03400000184774399
Regular Q-learning,100,906,0.03500000014901161
Regular Q-learning,100,907,0.03799999877810478
Regular Q-learning,100,908,0.03999999910593033
Regular Q-learning,100,909,0.032999999821186066
Regular Q-learning,100,910,0.0430000014603138
Regular Q-learning,100,911,0.03400000184774399
Regular Q-learning,100,912,0.03999999910593033
Regular Q-learning,100,913,0.03500000014901161
Regular Q-learning,100,914,0.03999999910593033
Regular Q-learning,100,915,0.03500000014901161
Regular Q-learning,100,916,0.039000000804662704
Regular Q-learning,100,917,0.03700000047683716
Regular Q-learning,100,918,0.04100000113248825
Regular Q-learning,100,919,0.03400000184774399
Regular Q-learning,100,920,0.03700000047683716
Regular Q-learning,100,921,0.03700000047683716
Regular Q-learning,100,922,0.03700000047683716
Regular Q-learning,100,923,0.03500000014901161
Regular Q-learning,100,924,0.035999998450279236
Regular Q-learning,100,925,0.035999998450279236
Regular Q-learning,100,926,0.03999999910593033
Regular Q-learning,100,927,0.03799999877810478
Regular Q-learning,100,928,0.035999998450279236
Regular Q-learning,100,929,0.03700000047683716
Regular Q-learning,100,930,0.039000000804662704
Regular Q-learning,100,931,0.03500000014901161
Regular Q-learning,100,932,0.03700000047683716
Regular Q-learning,100,933,0.03500000014901161
Regular Q-learning,100,934,0.03799999877810478
Regular Q-learning,100,935,0.03799999877810478
Regular Q-learning,100,936,0.03999999910593033
Regular Q-learning,100,937,0.032999999821186066
Regular Q-learning,100,938,0.039000000804662704
Regular Q-learning,100,939,0.03700000047683716
Regular Q-learning,100,940,0.039000000804662704
Regular Q-learning,100,941,0.03200000151991844
Regular Q-learning,100,942,0.03799999877810478
Regular Q-learning,100,943,0.03700000047683716
Regular Q-learning,100,944,0.04100000113248825
Regular Q-learning,100,945,0.03200000151991844
Regular Q-learning,100,946,0.039000000804662704
Regular Q-learning,100,947,0.03799999877810478
Regular Q-learning,100,948,0.041999999433755875
Regular Q-learning,100,949,0.029999999329447746
Regular Q-learning,100,950,0.03799999877810478
Regular Q-learning,100,951,0.035999998450279236
Regular Q-learning,100,952,0.04100000113248825
Regular Q-learning,100,953,0.03200000151991844
Regular Q-learning,100,954,0.03799999877810478
Regular Q-learning,100,955,0.035999998450279236
Regular Q-learning,100,956,0.04100000113248825
Regular Q-learning,100,957,0.03099999949336052
Regular Q-learning,100,958,0.03500000014901161
Regular Q-learning,100,959,0.039000000804662704
Regular Q-learning,100,960,0.03700000047683716
Regular Q-learning,100,961,0.03099999949336052
Regular Q-learning,100,962,0.03700000047683716
Regular Q-learning,100,963,0.03999999910593033
Regular Q-learning,100,964,0.03799999877810478
Regular Q-learning,100,965,0.03200000151991844
Regular Q-learning,100,966,0.035999998450279236
Regular Q-learning,100,967,0.039000000804662704
Regular Q-learning,100,968,0.03999999910593033
Regular Q-learning,100,969,0.03500000014901161
Regular Q-learning,100,970,0.03400000184774399
Regular Q-learning,100,971,0.03799999877810478
Regular Q-learning,100,972,0.039000000804662704
Regular Q-learning,100,973,0.03200000151991844
Regular Q-learning,100,974,0.03799999877810478
Regular Q-learning,100,975,0.04100000113248825
Regular Q-learning,100,976,0.03700000047683716
Regular Q-learning,100,977,0.03200000151991844
Regular Q-learning,100,978,0.03799999877810478
Regular Q-learning,100,979,0.039000000804662704
Regular Q-learning,100,980,0.03700000047683716
Regular Q-learning,100,981,0.03400000184774399
Regular Q-learning,100,982,0.03700000047683716
Regular Q-learning,100,983,0.039000000804662704
Regular Q-learning,100,984,0.03500000014901161
Regular Q-learning,100,985,0.03400000184774399
Regular Q-learning,100,986,0.035999998450279236
Regular Q-learning,100,987,0.039000000804662704
Regular Q-learning,100,988,0.032999999821186066
Regular Q-learning,100,989,0.03500000014901161
Regular Q-learning,100,990,0.03500000014901161
Regular Q-learning,100,991,0.03799999877810478
Regular Q-learning,100,992,0.035999998450279236
Regular Q-learning,100,993,0.03400000184774399
Regular Q-learning,100,994,0.03700000047683716
Regular Q-learning,100,995,0.03700000047683716
Regular Q-learning,100,996,0.035999998450279236
Regular Q-learning,100,997,0.032999999821186066
Regular Q-learning,100,998,0.032999999821186066
Regular Q-learning,100,999,0.03400000184774399
Regular Q-learning,100,1000,0.03799999877810478
Regular Q-learning,200,1,0.28200000524520874
Regular Q-learning,200,2,0.20800000429153442
Regular Q-learning,200,3,0.15199999511241913
Regular Q-learning,200,4,0.14100000262260437
Regular Q-learning,200,5,0.12099999934434891
Regular Q-learning,200,6,0.12999999523162842
Regular Q-learning,200,7,0.11699999868869781
Regular Q-learning,200,8,0.1420000046491623
Regular Q-learning,200,9,0.125
Regular Q-learning,200,10,0.13199999928474426
Regular Q-learning,200,11,0.12600000202655792
Regular Q-learning,200,12,0.14100000262260437
Regular Q-learning,200,13,0.12999999523162842
Regular Q-learning,200,14,0.1289999932050705
Regular Q-learning,200,15,0.1289999932050705
Regular Q-learning,200,16,0.13600000739097595
Regular Q-learning,200,17,0.12200000137090683
Regular Q-learning,200,18,0.1289999932050705
Regular Q-learning,200,19,0.13600000739097595
Regular Q-learning,200,20,0.12200000137090683
Regular Q-learning,200,21,0.11999999731779099
Regular Q-learning,200,22,0.125
Regular Q-learning,200,23,0.11500000208616257
Regular Q-learning,200,24,0.11500000208616257
Regular Q-learning,200,25,0.11900000274181366
Regular Q-learning,200,26,0.11400000005960464
Regular Q-learning,200,27,0.11299999803304672
Regular Q-learning,200,28,0.10999999940395355
Regular Q-learning,200,29,0.09799999743700027
Regular Q-learning,200,30,0.10499999672174454
Regular Q-learning,200,31,0.10700000077486038
Regular Q-learning,200,32,0.10100000351667404
Regular Q-learning,200,33,0.09200000017881393
Regular Q-learning,200,34,0.10100000351667404
Regular Q-learning,200,35,0.10000000149011612
Regular Q-learning,200,36,0.09399999678134918
Regular Q-learning,200,37,0.08900000154972076
Regular Q-learning,200,38,0.09300000220537186
Regular Q-learning,200,39,0.09399999678134918
Regular Q-learning,200,40,0.09700000286102295
Regular Q-learning,200,41,0.0820000022649765
Regular Q-learning,200,42,0.08799999952316284
Regular Q-learning,200,43,0.0820000022649765
Regular Q-learning,200,44,0.0860000029206276
Regular Q-learning,200,45,0.0860000029206276
Regular Q-learning,200,46,0.07699999958276749
Regular Q-learning,200,47,0.07599999755620956
Regular Q-learning,200,48,0.08100000023841858
Regular Q-learning,200,49,0.08299999684095383
Regular Q-learning,200,50,0.07500000298023224
Regular Q-learning,200,51,0.06599999964237213
Regular Q-learning,200,52,0.07699999958276749
Regular Q-learning,200,53,0.06800000369548798
Regular Q-learning,200,54,0.07699999958276749
Regular Q-learning,200,55,0.07100000232458115
Regular Q-learning,200,56,0.0820000022649765
Regular Q-learning,200,57,0.05999999865889549
Regular Q-learning,200,58,0.06499999761581421
Regular Q-learning,200,59,0.05999999865889549
Regular Q-learning,200,60,0.06800000369548798
Regular Q-learning,200,61,0.05999999865889549
Regular Q-learning,200,62,0.06800000369548798
Regular Q-learning,200,63,0.05400000140070915
Regular Q-learning,200,64,0.0729999989271164
Regular Q-learning,200,65,0.054999999701976776
Regular Q-learning,200,66,0.07199999690055847
Regular Q-learning,200,67,0.06599999964237213
Regular Q-learning,200,68,0.05999999865889549
Regular Q-learning,200,69,0.05900000035762787
Regular Q-learning,200,70,0.05999999865889549
Regular Q-learning,200,71,0.05999999865889549
Regular Q-learning,200,72,0.061000000685453415
Regular Q-learning,200,73,0.057999998331069946
Regular Q-learning,200,74,0.06199999898672104
Regular Q-learning,200,75,0.05700000002980232
Regular Q-learning,200,76,0.057999998331069946
Regular Q-learning,200,77,0.061000000685453415
Regular Q-learning,200,78,0.06499999761581421
Regular Q-learning,200,79,0.05700000002980232
Regular Q-learning,200,80,0.057999998331069946
Regular Q-learning,200,81,0.057999998331069946
Regular Q-learning,200,82,0.054999999701976776
Regular Q-learning,200,83,0.05299999937415123
Regular Q-learning,200,84,0.04899999871850014
Regular Q-learning,200,85,0.05299999937415123
Regular Q-learning,200,86,0.05400000140070915
Regular Q-learning,200,87,0.05400000140070915
Regular Q-learning,200,88,0.05400000140070915
Regular Q-learning,200,89,0.05700000002980232
Regular Q-learning,200,90,0.05000000074505806
Regular Q-learning,200,91,0.05700000002980232
Regular Q-learning,200,92,0.05000000074505806
Regular Q-learning,200,93,0.05299999937415123
Regular Q-learning,200,94,0.052000001072883606
Regular Q-learning,200,95,0.0560000017285347
Regular Q-learning,200,96,0.04600000008940697
Regular Q-learning,200,97,0.0560000017285347
Regular Q-learning,200,98,0.04800000041723251
Regular Q-learning,200,99,0.054999999701976776
Regular Q-learning,200,100,0.04500000178813934
Regular Q-learning,200,101,0.05400000140070915
Regular Q-learning,200,102,0.05000000074505806
Regular Q-learning,200,103,0.052000001072883606
Regular Q-learning,200,104,0.05000000074505806
Regular Q-learning,200,105,0.0560000017285347
Regular Q-learning,200,106,0.05299999937415123
Regular Q-learning,200,107,0.04500000178813934
Regular Q-learning,200,108,0.04699999839067459
Regular Q-learning,200,109,0.05299999937415123
Regular Q-learning,200,110,0.04500000178813934
Regular Q-learning,200,111,0.052000001072883606
Regular Q-learning,200,112,0.04699999839067459
Regular Q-learning,200,113,0.04899999871850014
Regular Q-learning,200,114,0.04800000041723251
Regular Q-learning,200,115,0.05000000074505806
Regular Q-learning,200,116,0.04500000178813934
Regular Q-learning,200,117,0.052000001072883606
Regular Q-learning,200,118,0.04500000178813934
Regular Q-learning,200,119,0.04500000178813934
Regular Q-learning,200,120,0.04600000008940697
Regular Q-learning,200,121,0.04500000178813934
Regular Q-learning,200,122,0.04399999976158142
Regular Q-learning,200,123,0.04699999839067459
Regular Q-learning,200,124,0.0430000014603138
Regular Q-learning,200,125,0.04800000041723251
Regular Q-learning,200,126,0.041999999433755875
Regular Q-learning,200,127,0.04899999871850014
Regular Q-learning,200,128,0.04500000178813934
Regular Q-learning,200,129,0.04800000041723251
Regular Q-learning,200,130,0.04100000113248825
Regular Q-learning,200,131,0.04699999839067459
Regular Q-learning,200,132,0.04800000041723251
Regular Q-learning,200,133,0.04399999976158142
Regular Q-learning,200,134,0.041999999433755875
Regular Q-learning,200,135,0.04500000178813934
Regular Q-learning,200,136,0.039000000804662704
Regular Q-learning,200,137,0.04500000178813934
Regular Q-learning,200,138,0.04399999976158142
Regular Q-learning,200,139,0.04800000041723251
Regular Q-learning,200,140,0.041999999433755875
Regular Q-learning,200,141,0.052000001072883606
Regular Q-learning,200,142,0.04699999839067459
Regular Q-learning,200,143,0.04699999839067459
Regular Q-learning,200,144,0.0430000014603138
Regular Q-learning,200,145,0.04899999871850014
Regular Q-learning,200,146,0.041999999433755875
Regular Q-learning,200,147,0.04600000008940697
Regular Q-learning,200,148,0.04399999976158142
Regular Q-learning,200,149,0.05299999937415123
Regular Q-learning,200,150,0.039000000804662704
Regular Q-learning,200,151,0.04600000008940697
Regular Q-learning,200,152,0.04500000178813934
Regular Q-learning,200,153,0.04899999871850014
Regular Q-learning,200,154,0.04399999976158142
Regular Q-learning,200,155,0.052000001072883606
Regular Q-learning,200,156,0.04399999976158142
Regular Q-learning,200,157,0.04899999871850014
Regular Q-learning,200,158,0.04500000178813934
Regular Q-learning,200,159,0.050999999046325684
Regular Q-learning,200,160,0.04899999871850014
Regular Q-learning,200,161,0.04699999839067459
Regular Q-learning,200,162,0.03999999910593033
Regular Q-learning,200,163,0.05000000074505806
Regular Q-learning,200,164,0.04399999976158142
Regular Q-learning,200,165,0.04600000008940697
Regular Q-learning,200,166,0.041999999433755875
Regular Q-learning,200,167,0.04800000041723251
Regular Q-learning,200,168,0.0430000014603138
Regular Q-learning,200,169,0.0430000014603138
Regular Q-learning,200,170,0.041999999433755875
Regular Q-learning,200,171,0.04600000008940697
Regular Q-learning,200,172,0.04399999976158142
Regular Q-learning,200,173,0.04500000178813934
Regular Q-learning,200,174,0.03999999910593033
Regular Q-learning,200,175,0.04500000178813934
Regular Q-learning,200,176,0.04899999871850014
Regular Q-learning,200,177,0.041999999433755875
Regular Q-learning,200,178,0.04399999976158142
Regular Q-learning,200,179,0.04600000008940697
Regular Q-learning,200,180,0.04100000113248825
Regular Q-learning,200,181,0.04800000041723251
Regular Q-learning,200,182,0.039000000804662704
Regular Q-learning,200,183,0.04600000008940697
Regular Q-learning,200,184,0.04399999976158142
Regular Q-learning,200,185,0.04899999871850014
Regular Q-learning,200,186,0.04100000113248825
Regular Q-learning,200,187,0.05000000074505806
Regular Q-learning,200,188,0.04500000178813934
Regular Q-learning,200,189,0.04699999839067459
Regular Q-learning,200,190,0.039000000804662704
Regular Q-learning,200,191,0.04899999871850014
Regular Q-learning,200,192,0.0430000014603138
Regular Q-learning,200,193,0.04500000178813934
Regular Q-learning,200,194,0.04500000178813934
Regular Q-learning,200,195,0.04500000178813934
Regular Q-learning,200,196,0.04100000113248825
Regular Q-learning,200,197,0.04899999871850014
Regular Q-learning,200,198,0.04100000113248825
Regular Q-learning,200,199,0.04699999839067459
Regular Q-learning,200,200,0.0430000014603138
Regular Q-learning,200,201,0.04500000178813934
Regular Q-learning,200,202,0.04399999976158142
Regular Q-learning,200,203,0.04500000178813934
Regular Q-learning,200,204,0.0430000014603138
Regular Q-learning,200,205,0.04699999839067459
Regular Q-learning,200,206,0.03999999910593033
Regular Q-learning,200,207,0.04899999871850014
Regular Q-learning,200,208,0.039000000804662704
Regular Q-learning,200,209,0.0430000014603138
Regular Q-learning,200,210,0.039000000804662704
Regular Q-learning,200,211,0.04800000041723251
Regular Q-learning,200,212,0.04600000008940697
Regular Q-learning,200,213,0.0430000014603138
Regular Q-learning,200,214,0.04100000113248825
Regular Q-learning,200,215,0.04699999839067459
Regular Q-learning,200,216,0.041999999433755875
Regular Q-learning,200,217,0.041999999433755875
Regular Q-learning,200,218,0.03799999877810478
Regular Q-learning,200,219,0.04699999839067459
Regular Q-learning,200,220,0.04399999976158142
Regular Q-learning,200,221,0.041999999433755875
Regular Q-learning,200,222,0.04399999976158142
Regular Q-learning,200,223,0.04800000041723251
Regular Q-learning,200,224,0.041999999433755875
Regular Q-learning,200,225,0.04600000008940697
Regular Q-learning,200,226,0.04100000113248825
Regular Q-learning,200,227,0.04500000178813934
Regular Q-learning,200,228,0.04100000113248825
Regular Q-learning,200,229,0.04699999839067459
Regular Q-learning,200,230,0.04100000113248825
Regular Q-learning,200,231,0.04699999839067459
Regular Q-learning,200,232,0.04600000008940697
Regular Q-learning,200,233,0.04800000041723251
Regular Q-learning,200,234,0.039000000804662704
Regular Q-learning,200,235,0.04500000178813934
Regular Q-learning,200,236,0.0430000014603138
Regular Q-learning,200,237,0.04600000008940697
Regular Q-learning,200,238,0.04100000113248825
Regular Q-learning,200,239,0.04500000178813934
Regular Q-learning,200,240,0.0430000014603138
Regular Q-learning,200,241,0.04500000178813934
Regular Q-learning,200,242,0.03999999910593033
Regular Q-learning,200,243,0.04600000008940697
Regular Q-learning,200,244,0.04399999976158142
Regular Q-learning,200,245,0.04399999976158142
Regular Q-learning,200,246,0.0430000014603138
Regular Q-learning,200,247,0.041999999433755875
Regular Q-learning,200,248,0.0430000014603138
Regular Q-learning,200,249,0.04500000178813934
Regular Q-learning,200,250,0.04399999976158142
Regular Q-learning,200,251,0.04500000178813934
Regular Q-learning,200,252,0.04500000178813934
Regular Q-learning,200,253,0.04399999976158142
Regular Q-learning,200,254,0.041999999433755875
Regular Q-learning,200,255,0.04100000113248825
Regular Q-learning,200,256,0.041999999433755875
Regular Q-learning,200,257,0.04699999839067459
Regular Q-learning,200,258,0.0430000014603138
Regular Q-learning,200,259,0.0430000014603138
Regular Q-learning,200,260,0.041999999433755875
Regular Q-learning,200,261,0.04500000178813934
Regular Q-learning,200,262,0.0430000014603138
Regular Q-learning,200,263,0.04100000113248825
Regular Q-learning,200,264,0.0430000014603138
Regular Q-learning,200,265,0.04600000008940697
Regular Q-learning,200,266,0.05000000074505806
Regular Q-learning,200,267,0.041999999433755875
Regular Q-learning,200,268,0.041999999433755875
Regular Q-learning,200,269,0.04699999839067459
Regular Q-learning,200,270,0.050999999046325684
Regular Q-learning,200,271,0.03999999910593033
Regular Q-learning,200,272,0.04399999976158142
Regular Q-learning,200,273,0.04800000041723251
Regular Q-learning,200,274,0.04600000008940697
Regular Q-learning,200,275,0.041999999433755875
Regular Q-learning,200,276,0.04699999839067459
Regular Q-learning,200,277,0.03799999877810478
Regular Q-learning,200,278,0.04699999839067459
Regular Q-learning,200,279,0.039000000804662704
Regular Q-learning,200,280,0.0430000014603138
Regular Q-learning,200,281,0.0430000014603138
Regular Q-learning,200,282,0.04600000008940697
Regular Q-learning,200,283,0.04500000178813934
Regular Q-learning,200,284,0.04399999976158142
Regular Q-learning,200,285,0.04500000178813934
Regular Q-learning,200,286,0.04600000008940697
Regular Q-learning,200,287,0.04399999976158142
Regular Q-learning,200,288,0.04399999976158142
Regular Q-learning,200,289,0.04500000178813934
Regular Q-learning,200,290,0.04699999839067459
Regular Q-learning,200,291,0.0430000014603138
Regular Q-learning,200,292,0.04500000178813934
Regular Q-learning,200,293,0.04600000008940697
Regular Q-learning,200,294,0.04500000178813934
Regular Q-learning,200,295,0.041999999433755875
Regular Q-learning,200,296,0.04500000178813934
Regular Q-learning,200,297,0.041999999433755875
Regular Q-learning,200,298,0.04600000008940697
Regular Q-learning,200,299,0.0430000014603138
Regular Q-learning,200,300,0.04100000113248825
Regular Q-learning,200,301,0.04100000113248825
Regular Q-learning,200,302,0.04800000041723251
Regular Q-learning,200,303,0.041999999433755875
Regular Q-learning,200,304,0.04600000008940697
Regular Q-learning,200,305,0.04100000113248825
Regular Q-learning,200,306,0.04699999839067459
Regular Q-learning,200,307,0.0430000014603138
Regular Q-learning,200,308,0.050999999046325684
Regular Q-learning,200,309,0.04500000178813934
Regular Q-learning,200,310,0.04699999839067459
Regular Q-learning,200,311,0.04399999976158142
Regular Q-learning,200,312,0.04399999976158142
Regular Q-learning,200,313,0.04399999976158142
Regular Q-learning,200,314,0.04399999976158142
Regular Q-learning,200,315,0.0430000014603138
Regular Q-learning,200,316,0.04699999839067459
Regular Q-learning,200,317,0.04399999976158142
Regular Q-learning,200,318,0.04500000178813934
Regular Q-learning,200,319,0.0430000014603138
Regular Q-learning,200,320,0.04500000178813934
Regular Q-learning,200,321,0.0430000014603138
Regular Q-learning,200,322,0.0430000014603138
Regular Q-learning,200,323,0.041999999433755875
Regular Q-learning,200,324,0.04800000041723251
Regular Q-learning,200,325,0.041999999433755875
Regular Q-learning,200,326,0.0430000014603138
Regular Q-learning,200,327,0.039000000804662704
Regular Q-learning,200,328,0.04899999871850014
Regular Q-learning,200,329,0.0430000014603138
Regular Q-learning,200,330,0.04399999976158142
Regular Q-learning,200,331,0.04100000113248825
Regular Q-learning,200,332,0.05000000074505806
Regular Q-learning,200,333,0.04500000178813934
Regular Q-learning,200,334,0.04100000113248825
Regular Q-learning,200,335,0.03999999910593033
Regular Q-learning,200,336,0.04699999839067459
Regular Q-learning,200,337,0.0430000014603138
Regular Q-learning,200,338,0.04500000178813934
Regular Q-learning,200,339,0.04100000113248825
Regular Q-learning,200,340,0.04600000008940697
Regular Q-learning,200,341,0.04399999976158142
Regular Q-learning,200,342,0.039000000804662704
Regular Q-learning,200,343,0.04399999976158142
Regular Q-learning,200,344,0.04899999871850014
Regular Q-learning,200,345,0.04100000113248825
Regular Q-learning,200,346,0.03799999877810478
Regular Q-learning,200,347,0.04800000041723251
Regular Q-learning,200,348,0.05000000074505806
Regular Q-learning,200,349,0.04399999976158142
Regular Q-learning,200,350,0.035999998450279236
Regular Q-learning,200,351,0.05000000074505806
Regular Q-learning,200,352,0.04600000008940697
Regular Q-learning,200,353,0.04399999976158142
Regular Q-learning,200,354,0.03700000047683716
Regular Q-learning,200,355,0.04800000041723251
Regular Q-learning,200,356,0.04500000178813934
Regular Q-learning,200,357,0.041999999433755875
Regular Q-learning,200,358,0.03700000047683716
Regular Q-learning,200,359,0.04600000008940697
Regular Q-learning,200,360,0.04600000008940697
Regular Q-learning,200,361,0.04399999976158142
Regular Q-learning,200,362,0.03500000014901161
Regular Q-learning,200,363,0.04800000041723251
Regular Q-learning,200,364,0.04100000113248825
Regular Q-learning,200,365,0.04699999839067459
Regular Q-learning,200,366,0.03700000047683716
Regular Q-learning,200,367,0.04699999839067459
Regular Q-learning,200,368,0.04699999839067459
Regular Q-learning,200,369,0.0430000014603138
Regular Q-learning,200,370,0.03500000014901161
Regular Q-learning,200,371,0.04800000041723251
Regular Q-learning,200,372,0.04399999976158142
Regular Q-learning,200,373,0.04399999976158142
Regular Q-learning,200,374,0.03700000047683716
Regular Q-learning,200,375,0.04699999839067459
Regular Q-learning,200,376,0.03999999910593033
Regular Q-learning,200,377,0.0430000014603138
Regular Q-learning,200,378,0.03799999877810478
Regular Q-learning,200,379,0.04800000041723251
Regular Q-learning,200,380,0.04600000008940697
Regular Q-learning,200,381,0.04399999976158142
Regular Q-learning,200,382,0.03700000047683716
Regular Q-learning,200,383,0.04399999976158142
Regular Q-learning,200,384,0.041999999433755875
Regular Q-learning,200,385,0.04399999976158142
Regular Q-learning,200,386,0.03700000047683716
Regular Q-learning,200,387,0.04399999976158142
Regular Q-learning,200,388,0.0430000014603138
Regular Q-learning,200,389,0.04399999976158142
Regular Q-learning,200,390,0.03799999877810478
Regular Q-learning,200,391,0.0430000014603138
Regular Q-learning,200,392,0.04399999976158142
Regular Q-learning,200,393,0.04500000178813934
Regular Q-learning,200,394,0.039000000804662704
Regular Q-learning,200,395,0.04399999976158142
Regular Q-learning,200,396,0.0430000014603138
Regular Q-learning,200,397,0.04399999976158142
Regular Q-learning,200,398,0.039000000804662704
Regular Q-learning,200,399,0.04600000008940697
Regular Q-learning,200,400,0.04399999976158142
Regular Q-learning,200,401,0.04600000008940697
Regular Q-learning,200,402,0.04100000113248825
Regular Q-learning,200,403,0.041999999433755875
Regular Q-learning,200,404,0.041999999433755875
Regular Q-learning,200,405,0.041999999433755875
Regular Q-learning,200,406,0.03999999910593033
Regular Q-learning,200,407,0.04500000178813934
Regular Q-learning,200,408,0.041999999433755875
Regular Q-learning,200,409,0.04100000113248825
Regular Q-learning,200,410,0.035999998450279236
Regular Q-learning,200,411,0.05000000074505806
Regular Q-learning,200,412,0.04399999976158142
Regular Q-learning,200,413,0.0430000014603138
Regular Q-learning,200,414,0.03500000014901161
Regular Q-learning,200,415,0.04699999839067459
Regular Q-learning,200,416,0.041999999433755875
Regular Q-learning,200,417,0.0430000014603138
Regular Q-learning,200,418,0.03700000047683716
Regular Q-learning,200,419,0.04800000041723251
Regular Q-learning,200,420,0.04100000113248825
Regular Q-learning,200,421,0.0430000014603138
Regular Q-learning,200,422,0.03999999910593033
Regular Q-learning,200,423,0.04800000041723251
Regular Q-learning,200,424,0.03999999910593033
Regular Q-learning,200,425,0.0430000014603138
Regular Q-learning,200,426,0.041999999433755875
Regular Q-learning,200,427,0.04699999839067459
Regular Q-learning,200,428,0.039000000804662704
Regular Q-learning,200,429,0.0430000014603138
Regular Q-learning,200,430,0.041999999433755875
Regular Q-learning,200,431,0.04600000008940697
Regular Q-learning,200,432,0.0430000014603138
Regular Q-learning,200,433,0.041999999433755875
Regular Q-learning,200,434,0.041999999433755875
Regular Q-learning,200,435,0.04600000008940697
Regular Q-learning,200,436,0.041999999433755875
Regular Q-learning,200,437,0.04399999976158142
Regular Q-learning,200,438,0.0430000014603138
Regular Q-learning,200,439,0.04600000008940697
Regular Q-learning,200,440,0.0430000014603138
Regular Q-learning,200,441,0.03999999910593033
Regular Q-learning,200,442,0.03999999910593033
Regular Q-learning,200,443,0.04500000178813934
Regular Q-learning,200,444,0.04100000113248825
Regular Q-learning,200,445,0.0430000014603138
Regular Q-learning,200,446,0.03999999910593033
Regular Q-learning,200,447,0.04600000008940697
Regular Q-learning,200,448,0.04100000113248825
Regular Q-learning,200,449,0.04100000113248825
Regular Q-learning,200,450,0.041999999433755875
Regular Q-learning,200,451,0.04399999976158142
Regular Q-learning,200,452,0.0430000014603138
Regular Q-learning,200,453,0.03799999877810478
Regular Q-learning,200,454,0.03999999910593033
Regular Q-learning,200,455,0.04500000178813934
Regular Q-learning,200,456,0.04399999976158142
Regular Q-learning,200,457,0.041999999433755875
Regular Q-learning,200,458,0.03700000047683716
Regular Q-learning,200,459,0.04500000178813934
Regular Q-learning,200,460,0.04399999976158142
Regular Q-learning,200,461,0.0430000014603138
Regular Q-learning,200,462,0.039000000804662704
Regular Q-learning,200,463,0.04800000041723251
Regular Q-learning,200,464,0.04600000008940697
Regular Q-learning,200,465,0.03999999910593033
Regular Q-learning,200,466,0.03799999877810478
Regular Q-learning,200,467,0.04500000178813934
Regular Q-learning,200,468,0.04399999976158142
Regular Q-learning,200,469,0.03999999910593033
Regular Q-learning,200,470,0.03799999877810478
Regular Q-learning,200,471,0.04600000008940697
Regular Q-learning,200,472,0.04399999976158142
Regular Q-learning,200,473,0.03999999910593033
Regular Q-learning,200,474,0.035999998450279236
Regular Q-learning,200,475,0.04800000041723251
Regular Q-learning,200,476,0.0430000014603138
Regular Q-learning,200,477,0.0430000014603138
Regular Q-learning,200,478,0.03700000047683716
Regular Q-learning,200,479,0.04600000008940697
Regular Q-learning,200,480,0.04100000113248825
Regular Q-learning,200,481,0.041999999433755875
Regular Q-learning,200,482,0.035999998450279236
Regular Q-learning,200,483,0.0430000014603138
Regular Q-learning,200,484,0.0430000014603138
Regular Q-learning,200,485,0.041999999433755875
Regular Q-learning,200,486,0.035999998450279236
Regular Q-learning,200,487,0.04600000008940697
Regular Q-learning,200,488,0.04399999976158142
Regular Q-learning,200,489,0.03799999877810478
Regular Q-learning,200,490,0.03700000047683716
Regular Q-learning,200,491,0.04500000178813934
Regular Q-learning,200,492,0.04500000178813934
Regular Q-learning,200,493,0.04100000113248825
Regular Q-learning,200,494,0.03500000014901161
Regular Q-learning,200,495,0.04500000178813934
Regular Q-learning,200,496,0.04699999839067459
Regular Q-learning,200,497,0.041999999433755875
Regular Q-learning,200,498,0.032999999821186066
Regular Q-learning,200,499,0.04699999839067459
Regular Q-learning,200,500,0.04600000008940697
Regular Q-learning,200,501,0.03999999910593033
Regular Q-learning,200,502,0.03799999877810478
Regular Q-learning,200,503,0.04600000008940697
Regular Q-learning,200,504,0.041999999433755875
Regular Q-learning,200,505,0.041999999433755875
Regular Q-learning,200,506,0.03700000047683716
Regular Q-learning,200,507,0.04600000008940697
Regular Q-learning,200,508,0.039000000804662704
Regular Q-learning,200,509,0.041999999433755875
Regular Q-learning,200,510,0.039000000804662704
Regular Q-learning,200,511,0.04600000008940697
Regular Q-learning,200,512,0.03999999910593033
Regular Q-learning,200,513,0.041999999433755875
Regular Q-learning,200,514,0.039000000804662704
Regular Q-learning,200,515,0.04500000178813934
Regular Q-learning,200,516,0.03999999910593033
Regular Q-learning,200,517,0.04100000113248825
Regular Q-learning,200,518,0.03799999877810478
Regular Q-learning,200,519,0.04500000178813934
Regular Q-learning,200,520,0.04100000113248825
Regular Q-learning,200,521,0.04399999976158142
Regular Q-learning,200,522,0.035999998450279236
Regular Q-learning,200,523,0.04100000113248825
Regular Q-learning,200,524,0.0430000014603138
Regular Q-learning,200,525,0.04399999976158142
Regular Q-learning,200,526,0.03400000184774399
Regular Q-learning,200,527,0.039000000804662704
Regular Q-learning,200,528,0.04500000178813934
Regular Q-learning,200,529,0.04600000008940697
Regular Q-learning,200,530,0.03500000014901161
Regular Q-learning,200,531,0.041999999433755875
Regular Q-learning,200,532,0.0430000014603138
Regular Q-learning,200,533,0.04500000178813934
Regular Q-learning,200,534,0.035999998450279236
Regular Q-learning,200,535,0.039000000804662704
Regular Q-learning,200,536,0.04600000008940697
Regular Q-learning,200,537,0.041999999433755875
Regular Q-learning,200,538,0.03799999877810478
Regular Q-learning,200,539,0.04399999976158142
Regular Q-learning,200,540,0.041999999433755875
Regular Q-learning,200,541,0.039000000804662704
Regular Q-learning,200,542,0.03999999910593033
Regular Q-learning,200,543,0.04500000178813934
Regular Q-learning,200,544,0.04800000041723251
Regular Q-learning,200,545,0.039000000804662704
Regular Q-learning,200,546,0.035999998450279236
Regular Q-learning,200,547,0.0430000014603138
Regular Q-learning,200,548,0.03999999910593033
Regular Q-learning,200,549,0.03999999910593033
Regular Q-learning,200,550,0.039000000804662704
Regular Q-learning,200,551,0.04500000178813934
Regular Q-learning,200,552,0.041999999433755875
Regular Q-learning,200,553,0.03799999877810478
Regular Q-learning,200,554,0.039000000804662704
Regular Q-learning,200,555,0.0430000014603138
Regular Q-learning,200,556,0.0430000014603138
Regular Q-learning,200,557,0.035999998450279236
Regular Q-learning,200,558,0.041999999433755875
Regular Q-learning,200,559,0.03999999910593033
Regular Q-learning,200,560,0.04100000113248825
Regular Q-learning,200,561,0.03500000014901161
Regular Q-learning,200,562,0.039000000804662704
Regular Q-learning,200,563,0.041999999433755875
Regular Q-learning,200,564,0.04399999976158142
Regular Q-learning,200,565,0.035999998450279236
Regular Q-learning,200,566,0.03799999877810478
Regular Q-learning,200,567,0.039000000804662704
Regular Q-learning,200,568,0.04399999976158142
Regular Q-learning,200,569,0.03799999877810478
Regular Q-learning,200,570,0.04100000113248825
Regular Q-learning,200,571,0.03999999910593033
Regular Q-learning,200,572,0.041999999433755875
Regular Q-learning,200,573,0.03400000184774399
Regular Q-learning,200,574,0.04100000113248825
Regular Q-learning,200,575,0.039000000804662704
Regular Q-learning,200,576,0.0430000014603138
Regular Q-learning,200,577,0.03999999910593033
Regular Q-learning,200,578,0.04100000113248825
Regular Q-learning,200,579,0.03799999877810478
Regular Q-learning,200,580,0.04399999976158142
Regular Q-learning,200,581,0.03400000184774399
Regular Q-learning,200,582,0.03999999910593033
Regular Q-learning,200,583,0.03999999910593033
Regular Q-learning,200,584,0.04100000113248825
Regular Q-learning,200,585,0.039000000804662704
Regular Q-learning,200,586,0.04100000113248825
Regular Q-learning,200,587,0.039000000804662704
Regular Q-learning,200,588,0.0430000014603138
Regular Q-learning,200,589,0.03799999877810478
Regular Q-learning,200,590,0.04399999976158142
Regular Q-learning,200,591,0.03799999877810478
Regular Q-learning,200,592,0.0430000014603138
Regular Q-learning,200,593,0.039000000804662704
Regular Q-learning,200,594,0.0430000014603138
Regular Q-learning,200,595,0.03700000047683716
Regular Q-learning,200,596,0.04100000113248825
Regular Q-learning,200,597,0.04100000113248825
Regular Q-learning,200,598,0.03799999877810478
Regular Q-learning,200,599,0.03999999910593033
Regular Q-learning,200,600,0.039000000804662704
Regular Q-learning,200,601,0.04100000113248825
Regular Q-learning,200,602,0.03999999910593033
Regular Q-learning,200,603,0.039000000804662704
Regular Q-learning,200,604,0.03999999910593033
Regular Q-learning,200,605,0.03999999910593033
Regular Q-learning,200,606,0.0430000014603138
Regular Q-learning,200,607,0.03700000047683716
Regular Q-learning,200,608,0.035999998450279236
Regular Q-learning,200,609,0.041999999433755875
Regular Q-learning,200,610,0.041999999433755875
Regular Q-learning,200,611,0.03999999910593033
Regular Q-learning,200,612,0.03799999877810478
Regular Q-learning,200,613,0.039000000804662704
Regular Q-learning,200,614,0.0430000014603138
Regular Q-learning,200,615,0.04100000113248825
Regular Q-learning,200,616,0.03700000047683716
Regular Q-learning,200,617,0.03799999877810478
Regular Q-learning,200,618,0.04100000113248825
Regular Q-learning,200,619,0.04100000113248825
Regular Q-learning,200,620,0.035999998450279236
Regular Q-learning,200,621,0.03999999910593033
Regular Q-learning,200,622,0.041999999433755875
Regular Q-learning,200,623,0.039000000804662704
Regular Q-learning,200,624,0.035999998450279236
Regular Q-learning,200,625,0.03999999910593033
Regular Q-learning,200,626,0.041999999433755875
Regular Q-learning,200,627,0.03999999910593033
Regular Q-learning,200,628,0.035999998450279236
Regular Q-learning,200,629,0.039000000804662704
Regular Q-learning,200,630,0.04399999976158142
Regular Q-learning,200,631,0.03999999910593033
Regular Q-learning,200,632,0.035999998450279236
Regular Q-learning,200,633,0.039000000804662704
Regular Q-learning,200,634,0.0430000014603138
Regular Q-learning,200,635,0.041999999433755875
Regular Q-learning,200,636,0.03700000047683716
Regular Q-learning,200,637,0.035999998450279236
Regular Q-learning,200,638,0.04600000008940697
Regular Q-learning,200,639,0.039000000804662704
Regular Q-learning,200,640,0.03700000047683716
Regular Q-learning,200,641,0.032999999821186066
Regular Q-learning,200,642,0.04500000178813934
Regular Q-learning,200,643,0.03999999910593033
Regular Q-learning,200,644,0.035999998450279236
Regular Q-learning,200,645,0.032999999821186066
Regular Q-learning,200,646,0.04399999976158142
Regular Q-learning,200,647,0.03700000047683716
Regular Q-learning,200,648,0.03500000014901161
Regular Q-learning,200,649,0.03700000047683716
Regular Q-learning,200,650,0.0430000014603138
Regular Q-learning,200,651,0.03700000047683716
Regular Q-learning,200,652,0.03999999910593033
Regular Q-learning,200,653,0.03799999877810478
Regular Q-learning,200,654,0.03999999910593033
Regular Q-learning,200,655,0.04100000113248825
Regular Q-learning,200,656,0.035999998450279236
Regular Q-learning,200,657,0.039000000804662704
Regular Q-learning,200,658,0.04100000113248825
Regular Q-learning,200,659,0.03999999910593033
Regular Q-learning,200,660,0.035999998450279236
Regular Q-learning,200,661,0.03799999877810478
Regular Q-learning,200,662,0.035999998450279236
Regular Q-learning,200,663,0.0430000014603138
Regular Q-learning,200,664,0.039000000804662704
Regular Q-learning,200,665,0.03799999877810478
Regular Q-learning,200,666,0.039000000804662704
Regular Q-learning,200,667,0.035999998450279236
Regular Q-learning,200,668,0.035999998450279236
Regular Q-learning,200,669,0.03999999910593033
Regular Q-learning,200,670,0.03799999877810478
Regular Q-learning,200,671,0.03799999877810478
Regular Q-learning,200,672,0.035999998450279236
Regular Q-learning,200,673,0.03799999877810478
Regular Q-learning,200,674,0.03999999910593033
Regular Q-learning,200,675,0.039000000804662704
Regular Q-learning,200,676,0.03700000047683716
Regular Q-learning,200,677,0.041999999433755875
Regular Q-learning,200,678,0.039000000804662704
Regular Q-learning,200,679,0.03500000014901161
Regular Q-learning,200,680,0.039000000804662704
Regular Q-learning,200,681,0.04399999976158142
Regular Q-learning,200,682,0.03700000047683716
Regular Q-learning,200,683,0.03500000014901161
Regular Q-learning,200,684,0.04100000113248825
Regular Q-learning,200,685,0.04100000113248825
Regular Q-learning,200,686,0.03500000014901161
Regular Q-learning,200,687,0.035999998450279236
Regular Q-learning,200,688,0.039000000804662704
Regular Q-learning,200,689,0.039000000804662704
Regular Q-learning,200,690,0.039000000804662704
Regular Q-learning,200,691,0.03500000014901161
Regular Q-learning,200,692,0.039000000804662704
Regular Q-learning,200,693,0.03999999910593033
Regular Q-learning,200,694,0.0430000014603138
Regular Q-learning,200,695,0.035999998450279236
Regular Q-learning,200,696,0.03700000047683716
Regular Q-learning,200,697,0.04100000113248825
Regular Q-learning,200,698,0.039000000804662704
Regular Q-learning,200,699,0.03400000184774399
Regular Q-learning,200,700,0.039000000804662704
Regular Q-learning,200,701,0.03999999910593033
Regular Q-learning,200,702,0.04100000113248825
Regular Q-learning,200,703,0.03400000184774399
Regular Q-learning,200,704,0.03999999910593033
Regular Q-learning,200,705,0.03799999877810478
Regular Q-learning,200,706,0.039000000804662704
Regular Q-learning,200,707,0.03400000184774399
Regular Q-learning,200,708,0.039000000804662704
Regular Q-learning,200,709,0.039000000804662704
Regular Q-learning,200,710,0.039000000804662704
Regular Q-learning,200,711,0.03500000014901161
Regular Q-learning,200,712,0.03999999910593033
Regular Q-learning,200,713,0.039000000804662704
Regular Q-learning,200,714,0.03799999877810478
Regular Q-learning,200,715,0.039000000804662704
Regular Q-learning,200,716,0.039000000804662704
Regular Q-learning,200,717,0.03799999877810478
Regular Q-learning,200,718,0.039000000804662704
Regular Q-learning,200,719,0.03700000047683716
Regular Q-learning,200,720,0.03999999910593033
Regular Q-learning,200,721,0.039000000804662704
Regular Q-learning,200,722,0.039000000804662704
Regular Q-learning,200,723,0.03799999877810478
Regular Q-learning,200,724,0.041999999433755875
Regular Q-learning,200,725,0.03500000014901161
Regular Q-learning,200,726,0.03799999877810478
Regular Q-learning,200,727,0.03799999877810478
Regular Q-learning,200,728,0.03999999910593033
Regular Q-learning,200,729,0.035999998450279236
Regular Q-learning,200,730,0.03700000047683716
Regular Q-learning,200,731,0.03700000047683716
Regular Q-learning,200,732,0.04100000113248825
Regular Q-learning,200,733,0.039000000804662704
Regular Q-learning,200,734,0.03700000047683716
Regular Q-learning,200,735,0.03799999877810478
Regular Q-learning,200,736,0.04399999976158142
Regular Q-learning,200,737,0.03799999877810478
Regular Q-learning,200,738,0.03500000014901161
Regular Q-learning,200,739,0.03799999877810478
Regular Q-learning,200,740,0.039000000804662704
Regular Q-learning,200,741,0.03999999910593033
Regular Q-learning,200,742,0.03500000014901161
Regular Q-learning,200,743,0.04100000113248825
Regular Q-learning,200,744,0.039000000804662704
Regular Q-learning,200,745,0.035999998450279236
Regular Q-learning,200,746,0.032999999821186066
Regular Q-learning,200,747,0.0430000014603138
Regular Q-learning,200,748,0.03500000014901161
Regular Q-learning,200,749,0.04399999976158142
Regular Q-learning,200,750,0.039000000804662704
Regular Q-learning,200,751,0.03700000047683716
Regular Q-learning,200,752,0.03700000047683716
Regular Q-learning,200,753,0.04100000113248825
Regular Q-learning,200,754,0.032999999821186066
Regular Q-learning,200,755,0.041999999433755875
Regular Q-learning,200,756,0.039000000804662704
Regular Q-learning,200,757,0.039000000804662704
Regular Q-learning,200,758,0.03500000014901161
Regular Q-learning,200,759,0.041999999433755875
Regular Q-learning,200,760,0.03400000184774399
Regular Q-learning,200,761,0.04399999976158142
Regular Q-learning,200,762,0.03799999877810478
Regular Q-learning,200,763,0.035999998450279236
Regular Q-learning,200,764,0.03400000184774399
Regular Q-learning,200,765,0.04500000178813934
Regular Q-learning,200,766,0.039000000804662704
Regular Q-learning,200,767,0.03200000151991844
Regular Q-learning,200,768,0.03500000014901161
Regular Q-learning,200,769,0.04399999976158142
Regular Q-learning,200,770,0.03799999877810478
Regular Q-learning,200,771,0.03500000014901161
Regular Q-learning,200,772,0.03400000184774399
Regular Q-learning,200,773,0.04600000008940697
Regular Q-learning,200,774,0.03799999877810478
Regular Q-learning,200,775,0.032999999821186066
Regular Q-learning,200,776,0.03500000014901161
Regular Q-learning,200,777,0.04699999839067459
Regular Q-learning,200,778,0.03799999877810478
Regular Q-learning,200,779,0.03500000014901161
Regular Q-learning,200,780,0.032999999821186066
Regular Q-learning,200,781,0.04399999976158142
Regular Q-learning,200,782,0.03500000014901161
Regular Q-learning,200,783,0.035999998450279236
Regular Q-learning,200,784,0.03700000047683716
Regular Q-learning,200,785,0.0430000014603138
Regular Q-learning,200,786,0.03500000014901161
Regular Q-learning,200,787,0.035999998450279236
Regular Q-learning,200,788,0.03700000047683716
Regular Q-learning,200,789,0.041999999433755875
Regular Q-learning,200,790,0.035999998450279236
Regular Q-learning,200,791,0.035999998450279236
Regular Q-learning,200,792,0.035999998450279236
Regular Q-learning,200,793,0.041999999433755875
Regular Q-learning,200,794,0.03700000047683716
Regular Q-learning,200,795,0.03500000014901161
Regular Q-learning,200,796,0.041999999433755875
Regular Q-learning,200,797,0.039000000804662704
Regular Q-learning,200,798,0.032999999821186066
Regular Q-learning,200,799,0.03799999877810478
Regular Q-learning,200,800,0.039000000804662704
Regular Q-learning,200,801,0.03799999877810478
Regular Q-learning,200,802,0.03500000014901161
Regular Q-learning,200,803,0.039000000804662704
Regular Q-learning,200,804,0.03999999910593033
Regular Q-learning,200,805,0.03700000047683716
Regular Q-learning,200,806,0.03500000014901161
Regular Q-learning,200,807,0.039000000804662704
Regular Q-learning,200,808,0.041999999433755875
Regular Q-learning,200,809,0.035999998450279236
Regular Q-learning,200,810,0.03500000014901161
Regular Q-learning,200,811,0.03700000047683716
Regular Q-learning,200,812,0.041999999433755875
Regular Q-learning,200,813,0.03799999877810478
Regular Q-learning,200,814,0.03400000184774399
Regular Q-learning,200,815,0.03400000184774399
Regular Q-learning,200,816,0.0430000014603138
Regular Q-learning,200,817,0.039000000804662704
Regular Q-learning,200,818,0.03400000184774399
Regular Q-learning,200,819,0.035999998450279236
Regular Q-learning,200,820,0.04399999976158142
Regular Q-learning,200,821,0.03700000047683716
Regular Q-learning,200,822,0.03400000184774399
Regular Q-learning,200,823,0.03500000014901161
Regular Q-learning,200,824,0.0430000014603138
Regular Q-learning,200,825,0.03799999877810478
Regular Q-learning,200,826,0.03400000184774399
Regular Q-learning,200,827,0.035999998450279236
Regular Q-learning,200,828,0.041999999433755875
Regular Q-learning,200,829,0.032999999821186066
Regular Q-learning,200,830,0.03700000047683716
Regular Q-learning,200,831,0.039000000804662704
Regular Q-learning,200,832,0.04399999976158142
Regular Q-learning,200,833,0.03700000047683716
Regular Q-learning,200,834,0.03400000184774399
Regular Q-learning,200,835,0.03999999910593033
Regular Q-learning,200,836,0.03999999910593033
Regular Q-learning,200,837,0.035999998450279236
Regular Q-learning,200,838,0.03400000184774399
Regular Q-learning,200,839,0.03999999910593033
Regular Q-learning,200,840,0.04100000113248825
Regular Q-learning,200,841,0.03799999877810478
Regular Q-learning,200,842,0.03500000014901161
Regular Q-learning,200,843,0.03799999877810478
Regular Q-learning,200,844,0.04100000113248825
Regular Q-learning,200,845,0.03700000047683716
Regular Q-learning,200,846,0.03400000184774399
Regular Q-learning,200,847,0.03700000047683716
Regular Q-learning,200,848,0.04100000113248825
Regular Q-learning,200,849,0.03700000047683716
Regular Q-learning,200,850,0.03500000014901161
Regular Q-learning,200,851,0.03799999877810478
Regular Q-learning,200,852,0.0430000014603138
Regular Q-learning,200,853,0.035999998450279236
Regular Q-learning,200,854,0.03500000014901161
Regular Q-learning,200,855,0.03799999877810478
Regular Q-learning,200,856,0.041999999433755875
Regular Q-learning,200,857,0.03400000184774399
Regular Q-learning,200,858,0.035999998450279236
Regular Q-learning,200,859,0.03799999877810478
Regular Q-learning,200,860,0.041999999433755875
Regular Q-learning,200,861,0.035999998450279236
Regular Q-learning,200,862,0.03500000014901161
Regular Q-learning,200,863,0.03700000047683716
Regular Q-learning,200,864,0.041999999433755875
Regular Q-learning,200,865,0.03400000184774399
Regular Q-learning,200,866,0.039000000804662704
Regular Q-learning,200,867,0.0430000014603138
Regular Q-learning,200,868,0.039000000804662704
Regular Q-learning,200,869,0.032999999821186066
Regular Q-learning,200,870,0.03799999877810478
Regular Q-learning,200,871,0.03799999877810478
Regular Q-learning,200,872,0.035999998450279236
Regular Q-learning,200,873,0.03799999877810478
Regular Q-learning,200,874,0.03700000047683716
Regular Q-learning,200,875,0.03700000047683716
Regular Q-learning,200,876,0.03799999877810478
Regular Q-learning,200,877,0.03700000047683716
Regular Q-learning,200,878,0.03700000047683716
Regular Q-learning,200,879,0.039000000804662704
Regular Q-learning,200,880,0.03700000047683716
Regular Q-learning,200,881,0.035999998450279236
Regular Q-learning,200,882,0.035999998450279236
Regular Q-learning,200,883,0.03999999910593033
Regular Q-learning,200,884,0.039000000804662704
Regular Q-learning,200,885,0.03200000151991844
Regular Q-learning,200,886,0.03400000184774399
Regular Q-learning,200,887,0.039000000804662704
Regular Q-learning,200,888,0.04100000113248825
Regular Q-learning,200,889,0.035999998450279236
Regular Q-learning,200,890,0.03200000151991844
Regular Q-learning,200,891,0.03700000047683716
Regular Q-learning,200,892,0.04399999976158142
Regular Q-learning,200,893,0.032999999821186066
Regular Q-learning,200,894,0.032999999821186066
Regular Q-learning,200,895,0.03500000014901161
Regular Q-learning,200,896,0.04600000008940697
Regular Q-learning,200,897,0.035999998450279236
Regular Q-learning,200,898,0.03099999949336052
Regular Q-learning,200,899,0.03500000014901161
Regular Q-learning,200,900,0.04399999976158142
Regular Q-learning,200,901,0.03500000014901161
Regular Q-learning,200,902,0.03099999949336052
Regular Q-learning,200,903,0.03500000014901161
Regular Q-learning,200,904,0.04399999976158142
Regular Q-learning,200,905,0.03400000184774399
Regular Q-learning,200,906,0.03500000014901161
Regular Q-learning,200,907,0.032999999821186066
Regular Q-learning,200,908,0.03999999910593033
Regular Q-learning,200,909,0.03700000047683716
Regular Q-learning,200,910,0.032999999821186066
Regular Q-learning,200,911,0.035999998450279236
Regular Q-learning,200,912,0.04100000113248825
Regular Q-learning,200,913,0.03400000184774399
Regular Q-learning,200,914,0.03400000184774399
Regular Q-learning,200,915,0.03700000047683716
Regular Q-learning,200,916,0.03999999910593033
Regular Q-learning,200,917,0.035999998450279236
Regular Q-learning,200,918,0.03400000184774399
Regular Q-learning,200,919,0.03500000014901161
Regular Q-learning,200,920,0.04100000113248825
Regular Q-learning,200,921,0.03500000014901161
Regular Q-learning,200,922,0.03400000184774399
Regular Q-learning,200,923,0.03700000047683716
Regular Q-learning,200,924,0.039000000804662704
Regular Q-learning,200,925,0.03500000014901161
Regular Q-learning,200,926,0.03400000184774399
Regular Q-learning,200,927,0.03700000047683716
Regular Q-learning,200,928,0.03799999877810478
Regular Q-learning,200,929,0.03500000014901161
Regular Q-learning,200,930,0.035999998450279236
Regular Q-learning,200,931,0.03700000047683716
Regular Q-learning,200,932,0.03700000047683716
Regular Q-learning,200,933,0.03400000184774399
Regular Q-learning,200,934,0.03799999877810478
Regular Q-learning,200,935,0.039000000804662704
Regular Q-learning,200,936,0.03500000014901161
Regular Q-learning,200,937,0.03400000184774399
Regular Q-learning,200,938,0.039000000804662704
Regular Q-learning,200,939,0.03799999877810478
Regular Q-learning,200,940,0.03400000184774399
Regular Q-learning,200,941,0.035999998450279236
Regular Q-learning,200,942,0.039000000804662704
Regular Q-learning,200,943,0.03999999910593033
Regular Q-learning,200,944,0.03799999877810478
Regular Q-learning,200,945,0.03200000151991844
Regular Q-learning,200,946,0.039000000804662704
Regular Q-learning,200,947,0.03500000014901161
Regular Q-learning,200,948,0.03500000014901161
Regular Q-learning,200,949,0.03500000014901161
Regular Q-learning,200,950,0.03999999910593033
Regular Q-learning,200,951,0.035999998450279236
Regular Q-learning,200,952,0.035999998450279236
Regular Q-learning,200,953,0.035999998450279236
Regular Q-learning,200,954,0.03999999910593033
Regular Q-learning,200,955,0.03500000014901161
Regular Q-learning,200,956,0.03799999877810478
Regular Q-learning,200,957,0.03400000184774399
Regular Q-learning,200,958,0.03999999910593033
Regular Q-learning,200,959,0.03700000047683716
Regular Q-learning,200,960,0.03799999877810478
Regular Q-learning,200,961,0.03500000014901161
Regular Q-learning,200,962,0.03799999877810478
Regular Q-learning,200,963,0.03500000014901161
Regular Q-learning,200,964,0.039000000804662704
Regular Q-learning,200,965,0.03200000151991844
Regular Q-learning,200,966,0.03799999877810478
Regular Q-learning,200,967,0.032999999821186066
Regular Q-learning,200,968,0.03799999877810478
Regular Q-learning,200,969,0.032999999821186066
Regular Q-learning,200,970,0.039000000804662704
Regular Q-learning,200,971,0.032999999821186066
Regular Q-learning,200,972,0.03799999877810478
Regular Q-learning,200,973,0.03500000014901161
Regular Q-learning,200,974,0.04100000113248825
Regular Q-learning,200,975,0.03200000151991844
Regular Q-learning,200,976,0.03799999877810478
Regular Q-learning,200,977,0.035999998450279236
Regular Q-learning,200,978,0.03799999877810478
Regular Q-learning,200,979,0.03099999949336052
Regular Q-learning,200,980,0.03700000047683716
Regular Q-learning,200,981,0.03700000047683716
Regular Q-learning,200,982,0.039000000804662704
Regular Q-learning,200,983,0.03400000184774399
Regular Q-learning,200,984,0.03700000047683716
Regular Q-learning,200,985,0.03400000184774399
Regular Q-learning,200,986,0.03500000014901161
Regular Q-learning,200,987,0.03799999877810478
Regular Q-learning,200,988,0.03700000047683716
Regular Q-learning,200,989,0.03400000184774399
Regular Q-learning,200,990,0.03500000014901161
Regular Q-learning,200,991,0.03400000184774399
Regular Q-learning,200,992,0.03999999910593033
Regular Q-learning,200,993,0.035999998450279236
Regular Q-learning,200,994,0.03700000047683716
Regular Q-learning,200,995,0.032999999821186066
Regular Q-learning,200,996,0.03700000047683716
Regular Q-learning,200,997,0.03500000014901161
Regular Q-learning,200,998,0.03700000047683716
Regular Q-learning,200,999,0.03400000184774399
Regular Q-learning,200,1000,0.03700000047683716