Commit ·
17ffe17
1
Parent(s): 867d8c8
Upload 6 files
Browse files- q_learning/2/model_2.json +441 -0
- q_learning/3/model_3.json +0 -0
q_learning/2/model_2.json
ADDED
|
@@ -0,0 +1,441 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[[0, 4], [3, 6]], 0": -1,
|
| 3 |
+
"[[0, 4], [3, 3]], 1": 0.9302576847023112,
|
| 4 |
+
"[[0, 3], [3, 3]], 0": -0.8177845843160069,
|
| 5 |
+
"[[1, 5], [3, 0]], 1": 0.7454742563016235,
|
| 6 |
+
"[[1, 3], [5, 0]], 0": -0.7374978151527638,
|
| 7 |
+
"[[1, 3], [4, 0]], 1": 0.2789172690424788,
|
| 8 |
+
"[[0, 3], [4, 0]], 0": -0.5266172519373816,
|
| 9 |
+
"[[0, 3], [3, 0]], 1": 0.5278423398738646,
|
| 10 |
+
"[[0, 0], [3, 0]], 0": -0.3636625795516241,
|
| 11 |
+
"[[0, 0], [0, 0]], 1": 0.21244479111312464,
|
| 12 |
+
"[[6, 3], [3, 1]], 1": -1,
|
| 13 |
+
"[[5, 3], [3, 1]], 0": 0.9235301987051137,
|
| 14 |
+
"[[5, 3], [3, 0]], 1": -0.8969949407921723,
|
| 15 |
+
"[[3, 3], [4, 0]], 0": 0.8522462378792536,
|
| 16 |
+
"[[3, 3], [3, 0]], 1": -0.8059059509403692,
|
| 17 |
+
"[[1, 3], [4, 0]], 0": 0.7283406027755861,
|
| 18 |
+
"[[1, 3], [3, 0]], 1": -0.6553800553336595,
|
| 19 |
+
"[[1, 0], [3, 0]], 0": 0.5774832169282763,
|
| 20 |
+
"[[1, 0], [0, 0]], 1": 0.19245844465956446,
|
| 21 |
+
"[[0, 0], [0, 0]], 0": 0.6229441196577291,
|
| 22 |
+
"[[6, 3], [4, 1]], 1": -1,
|
| 23 |
+
"[[5, 3], [4, 1]], 0": 0.9499963046503288,
|
| 24 |
+
"[[5, 3], [3, 1]], 1": -0.8109189874403576,
|
| 25 |
+
"[[3, 3], [4, 1]], 0": 0.75903677551063,
|
| 26 |
+
"[[3, 3], [3, 1]], 1": -0.7275928738987646,
|
| 27 |
+
"[[1, 3], [4, 1]], 0": 0.6866285269445205,
|
| 28 |
+
"[[3, 4], [3, 6]], 0": -1,
|
| 29 |
+
"[[3, 4], [3, 3]], 1": 0.9496010338197083,
|
| 30 |
+
"[[1, 4], [4, 3]], 0": -0.9024115756816693,
|
| 31 |
+
"[[1, 4], [3, 3]], 1": 0.8571463785132235,
|
| 32 |
+
"[[1, 3], [3, 3]], 0": -0.8116838900762556,
|
| 33 |
+
"[[1, 3], [0, 3]], 1": 0.8333738245079992,
|
| 34 |
+
"[[0, 3], [0, 3]], 0": -0.8174660955536757,
|
| 35 |
+
"[[1, 3], [0, 1]], 1": 0.7918539161914082,
|
| 36 |
+
"[[1, 2], [0, 1]], 0": -0.36563215157116935,
|
| 37 |
+
"[[1, 2], [0, 0]], 1": 0.39098780969859603,
|
| 38 |
+
"[[1, 0], [0, 1]], 0": -0.43985309667775463,
|
| 39 |
+
"[[1, 0], [0, 6]], 0": -1,
|
| 40 |
+
"[[1, 0], [0, 5]], 1": 0.93685077715905,
|
| 41 |
+
"[[0, 0], [0, 5]], 0": -0.8444316072126197,
|
| 42 |
+
"[[1, 0], [0, 3]], 1": 0.5966013876160413,
|
| 43 |
+
"[[0, 0], [0, 3]], 0": -0.7433798993767092,
|
| 44 |
+
"[[1, 0], [0, 1]], 1": 0.6619054885849132,
|
| 45 |
+
"[[0, 0], [0, 1]], 0": 0.5636463117000472,
|
| 46 |
+
"[[6, 3], [4, 0]], 1": -1,
|
| 47 |
+
"[[5, 3], [4, 0]], 0": 0.9499999999999995,
|
| 48 |
+
"[[0, 3], [4, 2]], 0": 0.7489522283209029,
|
| 49 |
+
"[[0, 5], [4, 0]], 1": -0.6918793337420449,
|
| 50 |
+
"[[0, 4], [4, 0]], 0": 0.6418178006498001,
|
| 51 |
+
"[[0, 4], [3, 0]], 1": -0.6009179252927568,
|
| 52 |
+
"[[0, 3], [3, 0]], 0": 0.5951146490832249,
|
| 53 |
+
"[[0, 3], [0, 0]], 1": -0.6637307164810375,
|
| 54 |
+
"[[0, 4], [3, 3]], 0": -0.8185412223848699,
|
| 55 |
+
"[[1, 4], [3, 1]], 1": 0.7794232812888924,
|
| 56 |
+
"[[1, 3], [3, 1]], 0": 0.662181613856816,
|
| 57 |
+
"[[1, 0], [2, 0]], 1": -0.5512615103398084,
|
| 58 |
+
"[[0, 0], [2, 0]], 0": 0.5593599127820815,
|
| 59 |
+
"[[0, 2], [0, 0]], 1": -0.6240626405958026,
|
| 60 |
+
"[[3, 3], [3, 6]], 0": -1,
|
| 61 |
+
"[[3, 3], [3, 3]], 1": 0.9311434362361692,
|
| 62 |
+
"[[1, 3], [4, 3]], 0": -0.8813416983979193,
|
| 63 |
+
"[[1, 3], [3, 3]], 1": 0.8388297403201121,
|
| 64 |
+
"[[1, 3], [3, 1]], 1": 0.7392805805516627,
|
| 65 |
+
"[[1, 2], [3, 1]], 0": -0.730128934573063,
|
| 66 |
+
"[[1, 2], [3, 0]], 1": 0.6750637205883194,
|
| 67 |
+
"[[1, 0], [3, 1]], 0": -0.4378718705420831,
|
| 68 |
+
"[[1, 0], [3, 0]], 1": 0.3964940733219504,
|
| 69 |
+
"[[0, 0], [6, 1]], 0": -1,
|
| 70 |
+
"[[2, 2], [3, 1]], 1": 0.9465781376815205,
|
| 71 |
+
"[[6, 0], [3, 3]], 1": -1,
|
| 72 |
+
"[[3, 0], [3, 3]], 0": 0.9499999995771913,
|
| 73 |
+
"[[3, 0], [3, 2]], 1": -0.9022595792107089,
|
| 74 |
+
"[[2, 0], [3, 2]], 0": 0.516005792942041,
|
| 75 |
+
"[[2, 0], [3, 1]], 1": 0.4111410306281762,
|
| 76 |
+
"[[6, 0], [4, 1]], 1": -1,
|
| 77 |
+
"[[5, 0], [4, 1]], 0": 0.6108832499999999,
|
| 78 |
+
"[[5, 0], [3, 1]], 1": -0.6355567048553751,
|
| 79 |
+
"[[3, 0], [4, 1]], 0": 0.495248954305748,
|
| 80 |
+
"[[3, 0], [3, 1]], 1": -0.37839224058383564,
|
| 81 |
+
"[[1, 0], [4, 1]], 0": 0.2658697825991968,
|
| 82 |
+
"[[1, 0], [3, 1]], 1": 0.7587998655983326,
|
| 83 |
+
"[[0, 0], [3, 1]], 0": -0.521639508382918,
|
| 84 |
+
"[[2, 0], [0, 1]], 1": 0.535485312149847,
|
| 85 |
+
"[[0, 2], [3, 6]], 0": -1,
|
| 86 |
+
"[[0, 2], [3, 3]], 1": 0.9499498953395571,
|
| 87 |
+
"[[0, 0], [3, 5]], 0": -0.9013619704845272,
|
| 88 |
+
"[[1, 0], [3, 3]], 1": 0.8543894004218506,
|
| 89 |
+
"[[0, 0], [3, 3]], 0": -0.8077916431476794,
|
| 90 |
+
"[[0, 6], [3, 2]], 1": -1,
|
| 91 |
+
"[[0, 5], [3, 2]], 0": 0.9365742866770137,
|
| 92 |
+
"[[0, 5], [2, 2]], 1": -0.6828299223393076,
|
| 93 |
+
"[[0, 4], [2, 2]], 0": 0.7828241636985297,
|
| 94 |
+
"[[0, 4], [2, 1]], 1": -0.861147331612588,
|
| 95 |
+
"[[0, 3], [2, 1]], 0": 0.8176686054898827,
|
| 96 |
+
"[[0, 3], [2, 0]], 1": -0.7030355717521153,
|
| 97 |
+
"[[6, 3], [3, 3]], 1": -1,
|
| 98 |
+
"[[3, 3], [3, 3]], 0": 0.8566142079599322,
|
| 99 |
+
"[[3, 3], [3, 2]], 1": -0.7215902372206435,
|
| 100 |
+
"[[2, 3], [3, 2]], 0": 0.6687764029418125,
|
| 101 |
+
"[[2, 3], [3, 1]], 1": -0.6721514223735485,
|
| 102 |
+
"[[1, 3], [6, 3]], 0": -1,
|
| 103 |
+
"[[1, 4], [4, 3]], 1": 0.949999999998085,
|
| 104 |
+
"[[6, 0], [4, 0]], 1": -1,
|
| 105 |
+
"[[5, 0], [4, 0]], 0": 0.9397298667899245,
|
| 106 |
+
"[[5, 0], [3, 0]], 1": -0.8752120818110256,
|
| 107 |
+
"[[3, 0], [4, 0]], 0": 0.8023450629864772,
|
| 108 |
+
"[[3, 0], [3, 0]], 1": -0.7436028244854795,
|
| 109 |
+
"[[1, 0], [4, 0]], 0": 0.5644448966535713,
|
| 110 |
+
"[[2, 0], [3, 1]], 0": 0.007145093176874996,
|
| 111 |
+
"[[2, 0], [3, 0]], 1": 0.12520512741528914,
|
| 112 |
+
"[[0, 3], [3, 6]], 0": -1,
|
| 113 |
+
"[[0, 5], [3, 3]], 1": 0.9187569014398895,
|
| 114 |
+
"[[0, 4], [3, 5]], 1": 0.9499957035446831,
|
| 115 |
+
"[[0, 3], [3, 5]], 0": -0.9024564717266015,
|
| 116 |
+
"[[0, 4], [0, 6]], 0": -1,
|
| 117 |
+
"[[0, 4], [0, 5]], 1": 0.9379092472345911,
|
| 118 |
+
"[[0, 3], [0, 5]], 0": -0.8591832823367906,
|
| 119 |
+
"[[0, 3], [0, 1]], 0": 0.7092993267099373,
|
| 120 |
+
"[[2, 3], [3, 1]], 0": 0.5378206944204326,
|
| 121 |
+
"[[2, 3], [3, 0]], 1": -0.06503225054662401,
|
| 122 |
+
"[[0, 3], [3, 2]], 0": 0.069953269623396,
|
| 123 |
+
"[[0, 3], [3, 1]], 1": 0.4834935203808032,
|
| 124 |
+
"[[0, 2], [3, 1]], 0": -0.4270432578833564,
|
| 125 |
+
"[[0, 2], [3, 0]], 1": 0.5012461785834417,
|
| 126 |
+
"[[2, 2], [0, 1]], 1": 0.395123140513973,
|
| 127 |
+
"[[0, 3], [4, 6]], 0": -1,
|
| 128 |
+
"[[1, 5], [4, 3]], 1": 0.9499805385088251,
|
| 129 |
+
"[[6, 0], [0, 0]], 1": -1,
|
| 130 |
+
"[[3, 0], [0, 2]], 0": 0.8323639954125,
|
| 131 |
+
"[[3, 0], [0, 1]], 1": -0.7770326635682547,
|
| 132 |
+
"[[1, 0], [2, 1]], 0": 0.6459848491674126,
|
| 133 |
+
"[[3, 3], [3, 1]], 0": 0.9499999998004196,
|
| 134 |
+
"[[0, 3], [0, 6]], 0": -1,
|
| 135 |
+
"[[0, 3], [0, 5]], 1": 0.8952343905,
|
| 136 |
+
"[[0, 2], [0, 5]], 0": -0.8808555545818201,
|
| 137 |
+
"[[1, 2], [0, 3]], 1": 0.8240360783992794,
|
| 138 |
+
"[[0, 2], [0, 3]], 0": -0.7634693368344985,
|
| 139 |
+
"[[1, 2], [0, 1]], 1": 0.6912453702070382,
|
| 140 |
+
"[[0, 2], [0, 1]], 0": 0.6664460587506678,
|
| 141 |
+
"[[3, 3], [0, 1]], 1": -0.8699628006931657,
|
| 142 |
+
"[[2, 3], [0, 1]], 0": 0.7943699049512163,
|
| 143 |
+
"[[2, 3], [0, 0]], 1": -0.6804980985497623,
|
| 144 |
+
"[[0, 3], [0, 2]], 0": 0.5890701054233614,
|
| 145 |
+
"[[0, 3], [0, 1]], 1": -0.6568783478943327,
|
| 146 |
+
"[[0, 2], [0, 6]], 0": -1,
|
| 147 |
+
"[[0, 2], [0, 3]], 1": 0.8382334499999999,
|
| 148 |
+
"[[3, 3], [4, 0]], 1": -0.6067089129277913,
|
| 149 |
+
"[[3, 0], [6, 0]], 0": -1,
|
| 150 |
+
"[[3, 2], [4, 0]], 1": 0.285,
|
| 151 |
+
"[[6, 3], [3, 0]], 1": -1,
|
| 152 |
+
"[[3, 3], [4, 2]], 0": 0.8289579325860872,
|
| 153 |
+
"[[0, 4], [0, 3]], 1": 0.9418282094199555,
|
| 154 |
+
"[[0, 3], [6, 2]], 0": -1,
|
| 155 |
+
"[[2, 4], [3, 2]], 1": 0.9435568808079344,
|
| 156 |
+
"[[0, 4], [0, 1]], 1": -0.7611154886403426,
|
| 157 |
+
"[[1, 3], [2, 3]], 1": 0.8298728872424224,
|
| 158 |
+
"[[0, 3], [2, 3]], 0": -0.7725733869598697,
|
| 159 |
+
"[[1, 3], [2, 1]], 1": 0.7316252244572041,
|
| 160 |
+
"[[0, 0], [5, 1]], 0": -0.4704264395258808,
|
| 161 |
+
"[[1, 3], [0, 6]], 0": -1,
|
| 162 |
+
"[[1, 3], [0, 5]], 1": 0.8837445735954086,
|
| 163 |
+
"[[6, 0], [3, 0]], 1": -1,
|
| 164 |
+
"[[3, 0], [3, 2]], 0": 0.6751783076530604,
|
| 165 |
+
"[[3, 0], [0, 2]], 1": -0.44573310552111156,
|
| 166 |
+
"[[2, 0], [0, 2]], 0": 0.2811659848240935,
|
| 167 |
+
"[[0, 6], [2, 3]], 1": -1,
|
| 168 |
+
"[[0, 5], [2, 3]], 0": 0.5647225284114813,
|
| 169 |
+
"[[1, 0], [3, 6]], 0": -1,
|
| 170 |
+
"[[1, 0], [3, 5]], 1": 0.9488697897054226,
|
| 171 |
+
"[[0, 6], [5, 0]], 1": -1,
|
| 172 |
+
"[[0, 5], [5, 0]], 0": 0.949956301279028,
|
| 173 |
+
"[[2, 3], [6, 0]], 0": -1,
|
| 174 |
+
"[[2, 3], [5, 0]], 1": 0.9499999999999995,
|
| 175 |
+
"[[3, 0], [4, 2]], 0": 0.9398669378558382,
|
| 176 |
+
"[[3, 0], [3, 0]], 0": 0.721905,
|
| 177 |
+
"[[3, 0], [0, 0]], 1": -0.8097916112565308,
|
| 178 |
+
"[[1, 0], [2, 0]], 0": 0.6867914346436943,
|
| 179 |
+
"[[0, 3], [0, 3]], 1": 0.9099219933334277,
|
| 180 |
+
"[[6, 3], [5, 1]], 1": -1,
|
| 181 |
+
"[[3, 3], [5, 1]], 0": 0.285,
|
| 182 |
+
"[[3, 3], [4, 1]], 1": -0.4849216265786296,
|
| 183 |
+
"[[3, 2], [4, 1]], 0": 0.2149034310747011,
|
| 184 |
+
"[[3, 2], [3, 1]], 1": -0.12517038930810542,
|
| 185 |
+
"[[1, 2], [4, 1]], 0": 0.06652453931377122,
|
| 186 |
+
"[[1, 2], [3, 1]], 1": 0.5206364672347132,
|
| 187 |
+
"[[0, 6], [4, 2]], 1": -1,
|
| 188 |
+
"[[0, 5], [4, 2]], 0": 0.9497787561233322,
|
| 189 |
+
"[[0, 5], [3, 2]], 1": -0.9024997687168992,
|
| 190 |
+
"[[0, 4], [3, 2]], 0": 0.8567805051763296,
|
| 191 |
+
"[[0, 4], [3, 1]], 1": -0.8421208903897883,
|
| 192 |
+
"[[0, 3], [3, 1]], 0": 0.4845859304101574,
|
| 193 |
+
"[[1, 3], [4, 6]], 0": -1,
|
| 194 |
+
"[[1, 3], [4, 5]], 1": 0.9499999999747066,
|
| 195 |
+
"[[0, 3], [4, 5]], 0": -0.902449953787079,
|
| 196 |
+
"[[1, 3], [4, 3]], 1": 0.7248271736571317,
|
| 197 |
+
"[[0, 3], [4, 3]], 0": -0.752255299964993,
|
| 198 |
+
"[[1, 3], [4, 1]], 1": 0.7390725016531898,
|
| 199 |
+
"[[0, 3], [4, 1]], 0": -0.7195182815260922,
|
| 200 |
+
"[[0, 4], [4, 2]], 1": 0.8841973315630067,
|
| 201 |
+
"[[0, 6], [3, 3]], 1": -1,
|
| 202 |
+
"[[0, 5], [3, 3]], 0": 0.9499999999782542,
|
| 203 |
+
"[[0, 5], [0, 2]], 1": -0.8164919717901689,
|
| 204 |
+
"[[0, 4], [0, 2]], 0": 0.6409125469199088,
|
| 205 |
+
"[[0, 3], [3, 3]], 1": 0.9436898097754371,
|
| 206 |
+
"[[0, 2], [3, 3]], 0": -0.6204637923579104,
|
| 207 |
+
"[[1, 0], [6, 0]], 0": -1,
|
| 208 |
+
"[[1, 2], [4, 0]], 1": 0.8449838671295546,
|
| 209 |
+
"[[0, 2], [4, 0]], 0": -0.6476377637097678,
|
| 210 |
+
"[[6, 0], [0, 1]], 1": -1,
|
| 211 |
+
"[[3, 0], [0, 1]], 0": 0.9231648513449999,
|
| 212 |
+
"[[1, 0], [6, 1]], 0": -1,
|
| 213 |
+
"[[1, 0], [5, 1]], 1": 0.9408185987313467,
|
| 214 |
+
"[[1, 3], [3, 6]], 0": -1,
|
| 215 |
+
"[[1, 3], [3, 5]], 1": 0.9340654343249621,
|
| 216 |
+
"[[0, 6], [0, 3]], 1": -1,
|
| 217 |
+
"[[0, 5], [0, 3]], 0": 0.8574933673762739,
|
| 218 |
+
"[[0, 4], [3, 5]], 0": 0.721905,
|
| 219 |
+
"[[1, 2], [0, 6]], 0": -1,
|
| 220 |
+
"[[1, 2], [0, 5]], 1": 0.9468428715958879,
|
| 221 |
+
"[[0, 6], [3, 0]], 1": -1,
|
| 222 |
+
"[[0, 4], [3, 1]], 0": 0.9499999999999995,
|
| 223 |
+
"[[2, 4], [0, 0]], 1": -0.5839380893820029,
|
| 224 |
+
"[[1, 5], [3, 3]], 1": 0.9066905736415498,
|
| 225 |
+
"[[1, 4], [3, 3]], 0": -0.41066872649999997,
|
| 226 |
+
"[[1, 4], [2, 3]], 1": 0.24810491402999996,
|
| 227 |
+
"[[1, 3], [2, 3]], 0": -0.28869322554989996,
|
| 228 |
+
"[[1, 4], [0, 3]], 1": 0.14909392817477232,
|
| 229 |
+
"[[0, 4], [0, 3]], 0": -0.07924921063915848,
|
| 230 |
+
"[[0, 4], [0, 2]], 1": 0.03550821243390909,
|
| 231 |
+
"[[1, 3], [2, 6]], 0": -1,
|
| 232 |
+
"[[1, 3], [2, 5]], 1": 0.9356178966331803,
|
| 233 |
+
"[[0, 3], [2, 5]], 0": -0.9004399944161796,
|
| 234 |
+
"[[1, 0], [2, 3]], 0": -0.01489183380999639,
|
| 235 |
+
"[[0, 3], [6, 0]], 0": -1,
|
| 236 |
+
"[[0, 4], [4, 0]], 1": 0.9499999999999995,
|
| 237 |
+
"[[0, 4], [3, 2]], 1": 0.7124231402067072,
|
| 238 |
+
"[[0, 5], [3, 0]], 1": -0.07065285881709912,
|
| 239 |
+
"[[0, 3], [5, 0]], 0": 0.06554681318560818,
|
| 240 |
+
"[[0, 3], [4, 0]], 1": 0.6176443100755349,
|
| 241 |
+
"[[0, 3], [2, 6]], 0": -1,
|
| 242 |
+
"[[1, 5], [2, 3]], 1": 0.9312153959414999,
|
| 243 |
+
"[[6, 3], [0, 0]], 1": -1,
|
| 244 |
+
"[[3, 3], [0, 2]], 0": 0.93685077715905,
|
| 245 |
+
"[[1, 4], [3, 6]], 0": -1,
|
| 246 |
+
"[[1, 4], [3, 5]], 1": 0.7903335,
|
| 247 |
+
"[[1, 3], [3, 5]], 0": -0.6680451821055524,
|
| 248 |
+
"[[1, 5], [0, 3]], 1": 0.9312153959414999,
|
| 249 |
+
"[[0, 3], [5, 1]], 0": 0.8370383626910038,
|
| 250 |
+
"[[6, 4], [3, 0]], 1": -1,
|
| 251 |
+
"[[3, 4], [3, 0]], 0": 0.948952655632987,
|
| 252 |
+
"[[3, 4], [2, 0]], 1": -0.8982265656536264,
|
| 253 |
+
"[[3, 3], [2, 0]], 0": 0.8499094595808518,
|
| 254 |
+
"[[3, 4], [0, 0]], 1": -0.8428299104473548,
|
| 255 |
+
"[[6, 0], [3, 1]], 1": -1,
|
| 256 |
+
"[[5, 0], [3, 1]], 0": 0.9357979393715077,
|
| 257 |
+
"[[2, 4], [3, 0]], 1": 0.9231648513449999,
|
| 258 |
+
"[[1, 2], [3, 6]], 0": -1,
|
| 259 |
+
"[[1, 2], [3, 5]], 1": 0.9231648513449999,
|
| 260 |
+
"[[0, 2], [3, 5]], 0": -0.7653116654759274,
|
| 261 |
+
"[[1, 2], [3, 3]], 1": 0.6586144656181437,
|
| 262 |
+
"[[0, 6], [4, 3]], 1": -1,
|
| 263 |
+
"[[0, 4], [4, 5]], 0": 0.9499785876267237,
|
| 264 |
+
"[[2, 4], [3, 6]], 0": -1,
|
| 265 |
+
"[[2, 4], [3, 3]], 1": 0.48449999999999993,
|
| 266 |
+
"[[3, 2], [4, 0]], 0": 0.8182888951787508,
|
| 267 |
+
"[[3, 2], [3, 0]], 1": -0.7709559240070801,
|
| 268 |
+
"[[1, 2], [4, 0]], 0": 0.7352704250396558,
|
| 269 |
+
"[[1, 6], [4, 0]], 1": -1,
|
| 270 |
+
"[[1, 5], [4, 0]], 0": 0.9047841408052598,
|
| 271 |
+
"[[5, 6], [3, 0]], 1": -1,
|
| 272 |
+
"[[5, 4], [3, 1]], 0": 0.285,
|
| 273 |
+
"[[5, 4], [3, 0]], 1": -0.08122499999999999,
|
| 274 |
+
"[[5, 3], [3, 0]], 0": 0.9499999999999995,
|
| 275 |
+
"[[5, 3], [0, 0]], 1": -0.894879488311969,
|
| 276 |
+
"[[3, 6], [0, 0]], 1": -1,
|
| 277 |
+
"[[3, 4], [0, 1]], 0": 0.9499999999999995,
|
| 278 |
+
"[[3, 6], [2, 0]], 1": -1,
|
| 279 |
+
"[[3, 4], [2, 1]], 0": 0.946865325603697,
|
| 280 |
+
"[[0, 5], [4, 3]], 1": 0.9496285670003843,
|
| 281 |
+
"[[0, 4], [4, 3]], 0": -0.9023542624436942,
|
| 282 |
+
"[[1, 0], [6, 3]], 0": -1,
|
| 283 |
+
"[[1, 0], [5, 3]], 1": 0.948453007081985,
|
| 284 |
+
"[[0, 0], [5, 3]], 0": -0.8937807534308735,
|
| 285 |
+
"[[1, 3], [5, 3]], 0": -0.6951908007301609,
|
| 286 |
+
"[[3, 0], [3, 1]], 0": 0.8594316660863829,
|
| 287 |
+
"[[6, 3], [5, 0]], 1": -1,
|
| 288 |
+
"[[3, 3], [5, 0]], 0": 0.9231648513449999,
|
| 289 |
+
"[[6, 2], [3, 3]], 1": -1,
|
| 290 |
+
"[[3, 2], [3, 3]], 0": 0.8382334499999999,
|
| 291 |
+
"[[3, 2], [3, 2]], 1": -0.6470564323094999,
|
| 292 |
+
"[[2, 2], [3, 2]], 0": 0.4327231051174928,
|
| 293 |
+
"[[1, 3], [6, 0]], 0": -1,
|
| 294 |
+
"[[1, 3], [5, 0]], 1": 0.8685780683249997,
|
| 295 |
+
"[[0, 3], [6, 1]], 0": -1,
|
| 296 |
+
"[[0, 4], [4, 1]], 1": 0.9262248892142428,
|
| 297 |
+
"[[2, 6], [3, 0]], 1": -1,
|
| 298 |
+
"[[2, 3], [5, 1]], 0": 0.5569398513449999,
|
| 299 |
+
"[[2, 6], [0, 3]], 1": -1,
|
| 300 |
+
"[[2, 5], [0, 3]], 0": 0.285,
|
| 301 |
+
"[[2, 5], [0, 2]], 1": -0.08122499999999999,
|
| 302 |
+
"[[2, 4], [0, 2]], 0": 0.023149124999999996,
|
| 303 |
+
"[[2, 4], [0, 1]], 1": -0.006597500624999998,
|
| 304 |
+
"[[0, 4], [2, 6]], 0": -1,
|
| 305 |
+
"[[0, 4], [2, 3]], 1": 0.9454898165655541,
|
| 306 |
+
"[[0, 6], [4, 0]], 1": -1,
|
| 307 |
+
"[[0, 4], [4, 1]], 0": 0.9499999998277211,
|
| 308 |
+
"[[0, 4], [4, 6]], 0": -1,
|
| 309 |
+
"[[0, 4], [4, 5]], 1": 0.9489171049573895,
|
| 310 |
+
"[[0, 4], [2, 5]], 1": 0.9498986384221031,
|
| 311 |
+
"[[1, 4], [4, 0]], 1": 0.9468428715958879,
|
| 312 |
+
"[[1, 3], [6, 1]], 0": -1,
|
| 313 |
+
"[[1, 4], [4, 1]], 1": 0.48449999999999993,
|
| 314 |
+
"[[0, 3], [3, 5]], 1": 0.62415,
|
| 315 |
+
"[[6, 2], [3, 1]], 1": -1,
|
| 316 |
+
"[[5, 2], [3, 1]], 0": 0.871763415,
|
| 317 |
+
"[[5, 2], [3, 0]], 1": -0.8901059114874352,
|
| 318 |
+
"[[1, 6], [3, 0]], 1": -1,
|
| 319 |
+
"[[1, 3], [5, 1]], 0": 0.62415,
|
| 320 |
+
"[[2, 3], [3, 6]], 0": -1,
|
| 321 |
+
"[[2, 3], [3, 5]], 1": 0.8382334499999999,
|
| 322 |
+
"[[2, 3], [3, 3]], 1": 0.871763415,
|
| 323 |
+
"[[3, 3], [0, 6]], 0": -1,
|
| 324 |
+
"[[3, 3], [0, 3]], 1": 0.62415,
|
| 325 |
+
"[[3, 3], [3, 2]], 0": 0.8576460174522162,
|
| 326 |
+
"[[3, 5], [3, 0]], 1": -0.8445802288013665,
|
| 327 |
+
"[[3, 3], [3, 5]], 1": 0.5386093875,
|
| 328 |
+
"[[1, 3], [4, 5]], 0": -0.32130295087499994,
|
| 329 |
+
"[[6, 2], [0, 3]], 1": -1,
|
| 330 |
+
"[[3, 2], [0, 3]], 0": 0.76654677585,
|
| 331 |
+
"[[3, 2], [0, 2]], 1": -0.7599093638657505,
|
| 332 |
+
"[[2, 2], [0, 2]], 0": 0.6564372318807887,
|
| 333 |
+
"[[3, 3], [6, 2]], 0": -1,
|
| 334 |
+
"[[3, 4], [4, 2]], 1": 0.7682208900999374,
|
| 335 |
+
"[[3, 6], [3, 3]], 1": -1,
|
| 336 |
+
"[[3, 4], [3, 5]], 0": 0.285,
|
| 337 |
+
"[[5, 4], [3, 3]], 1": -0.3937422487499999,
|
| 338 |
+
"[[3, 4], [4, 3]], 0": 0.22390690217624992,
|
| 339 |
+
"[[6, 3], [0, 1]], 1": -1,
|
| 340 |
+
"[[5, 3], [0, 1]], 0": 0.9159086980527134,
|
| 341 |
+
"[[0, 5], [4, 0]], 0": 0.9116640733499999,
|
| 342 |
+
"[[6, 4], [4, 3]], 1": -1,
|
| 343 |
+
"[[5, 4], [4, 3]], 0": 0.6647183249999999,
|
| 344 |
+
"[[6, 4], [3, 3]], 1": -1,
|
| 345 |
+
"[[3, 4], [3, 3]], 0": 0.8952343905,
|
| 346 |
+
"[[3, 4], [3, 2]], 1": -0.4879932207749999,
|
| 347 |
+
"[[5, 3], [6, 1]], 0": -1,
|
| 348 |
+
"[[5, 4], [4, 1]], 1": 0.285,
|
| 349 |
+
"[[0, 3], [4, 3]], 1": 0.285,
|
| 350 |
+
"[[0, 2], [4, 3]], 0": -0.08122499999999999,
|
| 351 |
+
"[[6, 4], [0, 1]], 1": -1,
|
| 352 |
+
"[[3, 6], [4, 0]], 1": -1,
|
| 353 |
+
"[[3, 4], [4, 1]], 0": 0.285,
|
| 354 |
+
"[[3, 4], [3, 1]], 1": -0.08122499999999999,
|
| 355 |
+
"[[6, 3], [3, 5]], 1": -1,
|
| 356 |
+
"[[3, 3], [3, 5]], 0": 0.7903335,
|
| 357 |
+
"[[5, 3], [3, 3]], 1": -0.7709618533652146,
|
| 358 |
+
"[[3, 3], [4, 3]], 0": 0.6395902757212077,
|
| 359 |
+
"[[0, 4], [4, 3]], 1": 0.9312153959414999,
|
| 360 |
+
"[[6, 3], [2, 1]], 1": -1,
|
| 361 |
+
"[[5, 3], [2, 1]], 0": 0.9492419734701725,
|
| 362 |
+
"[[5, 4], [0, 1]], 1": -0.8762145031848467,
|
| 363 |
+
"[[3, 3], [4, 6]], 0": -1,
|
| 364 |
+
"[[5, 5], [4, 3]], 1": 0.285,
|
| 365 |
+
"[[6, 3], [4, 3]], 1": -1,
|
| 366 |
+
"[[5, 3], [4, 3]], 0": 0.8952343905,
|
| 367 |
+
"[[3, 3], [4, 2]], 1": -0.015834001499999997,
|
| 368 |
+
"[[3, 5], [4, 0]], 0": 0.9494693814291206,
|
| 369 |
+
"[[6, 0], [0, 3]], 1": -1,
|
| 370 |
+
"[[3, 0], [0, 3]], 0": 0.48449999999999993,
|
| 371 |
+
"[[2, 0], [3, 6]], 0": -1,
|
| 372 |
+
"[[2, 0], [3, 3]], 1": 0.285,
|
| 373 |
+
"[[1, 0], [3, 3]], 0": -0.6296172721624684,
|
| 374 |
+
"[[3, 2], [3, 1]], 0": 0.928916847360425,
|
| 375 |
+
"[[3, 0], [2, 2]], 0": 0.8952343905,
|
| 376 |
+
"[[0, 3], [6, 5]], 0": -1,
|
| 377 |
+
"[[1, 0], [4, 3]], 0": -0.38670359559455647,
|
| 378 |
+
"[[3, 0], [3, 6]], 0": -1,
|
| 379 |
+
"[[3, 0], [3, 5]], 1": 0.285,
|
| 380 |
+
"[[1, 0], [4, 5]], 0": -0.08122499999999999,
|
| 381 |
+
"[[5, 3], [6, 0]], 0": -1,
|
| 382 |
+
"[[5, 4], [4, 0]], 1": 0.9116640733499999,
|
| 383 |
+
"[[2, 5], [3, 0]], 1": -0.7344624523127677,
|
| 384 |
+
"[[3, 3], [6, 0]], 0": -1,
|
| 385 |
+
"[[3, 4], [4, 0]], 1": 0.9231648513449999,
|
| 386 |
+
"[[6, 2], [4, 0]], 1": -1,
|
| 387 |
+
"[[5, 2], [4, 0]], 0": 0.9489171049573895,
|
| 388 |
+
"[[1, 6], [3, 3]], 1": -1,
|
| 389 |
+
"[[1, 3], [5, 5]], 0": 0.48449999999999993,
|
| 390 |
+
"[[3, 3], [6, 1]], 0": -1,
|
| 391 |
+
"[[3, 4], [4, 1]], 1": 0.62415,
|
| 392 |
+
"[[6, 4], [0, 3]], 1": -1,
|
| 393 |
+
"[[3, 4], [0, 3]], 0": 0.9194683634828844,
|
| 394 |
+
"[[6, 2], [3, 0]], 1": -1,
|
| 395 |
+
"[[3, 2], [4, 2]], 0": 0.62415,
|
| 396 |
+
"[[0, 3], [6, 3]], 0": -1,
|
| 397 |
+
"[[3, 0], [3, 3]], 1": 0.62415,
|
| 398 |
+
"[[1, 6], [5, 3]], 1": -1,
|
| 399 |
+
"[[1, 5], [5, 3]], 0": 0.48449999999999993,
|
| 400 |
+
"[[5, 4], [3, 1]], 1": -0.6774564968794798,
|
| 401 |
+
"[[2, 6], [0, 0]], 1": -1,
|
| 402 |
+
"[[2, 4], [0, 1]], 0": 0.9267897499740982,
|
| 403 |
+
"[[1, 6], [4, 3]], 1": -1,
|
| 404 |
+
"[[1, 5], [4, 3]], 0": 0.285,
|
| 405 |
+
"[[3, 2], [3, 2]], 0": 0.285,
|
| 406 |
+
"[[5, 0], [6, 0]], 0": -1,
|
| 407 |
+
"[[5, 2], [4, 0]], 1": 0.285,
|
| 408 |
+
"[[3, 3], [3, 0]], 0": 0.285,
|
| 409 |
+
"[[3, 3], [0, 0]], 1": -0.08122499999999999,
|
| 410 |
+
"[[0, 3], [2, 2]], 0": 0.023149124999999996,
|
| 411 |
+
"[[6, 3], [0, 3]], 1": -1,
|
| 412 |
+
"[[3, 3], [0, 3]], 0": 0.48449999999999993,
|
| 413 |
+
"[[3, 3], [0, 2]], 1": -0.08122499999999999,
|
| 414 |
+
"[[3, 4], [4, 2]], 0": 0.62415,
|
| 415 |
+
"[[6, 4], [4, 1]], 1": -1,
|
| 416 |
+
"[[5, 4], [4, 1]], 0": 0.721905,
|
| 417 |
+
"[[0, 0], [5, 0]], 0": -0.31699611008726963,
|
| 418 |
+
"[[1, 3], [5, 1]], 1": 0.62415,
|
| 419 |
+
"[[0, 5], [4, 3]], 0": 0.285,
|
| 420 |
+
"[[5, 6], [4, 0]], 1": -1,
|
| 421 |
+
"[[2, 3], [3, 3]], 0": -0.5771773039861278,
|
| 422 |
+
"[[2, 3], [3, 2]], 1": 0.291395998037597,
|
| 423 |
+
"[[2, 3], [5, 6]], 0": -1,
|
| 424 |
+
"[[2, 3], [5, 3]], 1": 0.285,
|
| 425 |
+
"[[3, 6], [5, 0]], 1": -1,
|
| 426 |
+
"[[3, 5], [5, 0]], 0": 0.285,
|
| 427 |
+
"[[3, 5], [4, 0]], 1": -0.08122499999999999,
|
| 428 |
+
"[[3, 4], [4, 0]], 0": 0.023149124999999996,
|
| 429 |
+
"[[3, 4], [3, 0]], 1": -0.006597500624999998,
|
| 430 |
+
"[[0, 4], [4, 2]], 0": 0.0018802876781249993,
|
| 431 |
+
"[[3, 5], [0, 3]], 1": 0.285,
|
| 432 |
+
"[[3, 3], [5, 1]], 1": 0.285,
|
| 433 |
+
"[[5, 3], [5, 0]], 0": 0.285,
|
| 434 |
+
"[[5, 3], [4, 0]], 1": -0.32760535066396673,
|
| 435 |
+
"[[5, 3], [3, 6]], 0": -1,
|
| 436 |
+
"[[5, 3], [3, 5]], 1": 0.285,
|
| 437 |
+
"[[3, 3], [4, 5]], 0": -0.08122499999999999,
|
| 438 |
+
"[[5, 3], [0, 1]], 1": -0.13808249999999997,
|
| 439 |
+
"[[3, 3], [2, 1]], 0": 0.039353512499999986,
|
| 440 |
+
"[[3, 4], [0, 1]], 1": -0.011215751062499994
|
| 441 |
+
}
|
q_learning/3/model_3.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|