{ "episodes": 50, "win_rate": 74.0, "avg_reward": 47.52314758300781, "reward_std": 4.412993431091309, "avg_steps": 745.1199951171875, "accuracy": 6.269073009490967, "smoothness": 0.3154057562351227, "all_rewards": [ 48.2906494140625, 50.77237319946289, 50.14163589477539, 48.947845458984378, 49.56505584716797, 40.190711975097659, 30.776613235473634, 43.29934310913086, 47.981441497802737, 49.36827850341797, 48.815887451171878, 43.059574127197269, 51.63787078857422, 48.71165466308594, 50.26890182495117, 50.41714096069336, 48.496063232421878, 50.46558380126953, 49.22118377685547, 45.535709381103519, 48.58135223388672, 47.9166259765625, 53.34693908691406, 48.824371337890628, 42.10444259643555, 48.9809684753418, 49.69679260253906, 47.24809646606445, 47.83368682861328, 50.96811294555664, 40.91338348388672, 50.311866760253909, 44.72077560424805, 32.812217712402347, 49.33613204956055, 38.193267822265628, 47.995086669921878, 45.43364715576172, 48.48876953125, 48.9103889465332, 49.801021575927737, 50.763526916503909, 46.787349700927737, 49.468013763427737, 50.883689880371097, 49.078697204589847, 49.72896957397461, 50.51682662963867, 49.93709945678711, 50.61183547973633 ], "all_wins": [ 1, 1, 1, 1, 1, 0, 0, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 0, 0, 1, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ], "all_steps": [ 274, 907, 672, 459, 610, 1001, 1001, 1001, 783, 603, 622, 1001, 710, 808, 528, 599, 479, 594, 564, 1001, 360, 1001, 935, 854, 1001, 602, 629, 582, 474, 785, 1001, 607, 1001, 1001, 778, 1001, 1001, 1001, 468, 596, 527, 701, 907, 829, 673, 490, 845, 893, 800, 696 ], "all_smoothness": [ 0.15145567059516908, 0.3853631913661957, 0.3750549554824829, 0.25761979818344118, 0.11545585095882416, 0.18385350704193116, 0.5048767924308777, 0.2567833960056305, 0.1962285190820694, 0.2489635944366455, 0.28981390595436098, 0.33890485763549807, 0.45375457406044009, 0.3328802287578583, 0.3824927508831024, 0.31483399868011477, 0.17336449027061463, 0.31308215856552126, 0.3127407729625702, 0.3592800498008728, 0.18878665566444398, 0.38333573937416079, 0.4916512668132782, 0.28407880663871767, 0.43397775292396548, 0.24284937977790833, 0.19558699429035188, 0.14971953630447389, 0.12153149396181107, 0.2865433990955353, 0.16715869307518006, 0.295793741941452, 0.3921850621700287, 0.4117676019668579, 0.22831128537654878, 0.42440998554229739, 0.5311110615730286, 0.4691881239414215, 0.10931486636400223, 0.26380860805511477, 0.29024505615234377, 0.39570915699005129, 0.14025920629501344, 0.21150551736354829, 0.3465195894241333, 0.2560855448246002, 0.4141657054424286, 0.2874036133289337, 0.3330134451389313, 0.2971930503845215 ], "all_accuracies": [ 11.029411315917969, 8.474575996398926, 6.666666507720947, 8.15217399597168, 9.259259223937989, 7.734806537628174, 3.076923131942749, 7.777777671813965, 9.740260124206543, 10.8695650100708, 8.108108520507813, 5.990783214569092, 5.319149017333984, 8.823529243469239, 8.15217399597168, 5.769230842590332, 12.195121765136719, 4.934210300445557, 7.4257426261901859, 5.204461097717285, 7.281553268432617, 3.0303030014038088, 3.7037036418914797, 8.15217399597168, 4.255319118499756, 6.25, 8.875740051269532, 15.0, 17.647058486938478, 4.545454502105713, 9.271523475646973, 4.411764621734619, 4.248365879058838, 2.5936598777770998, 7.009346008300781, 3.353658437728882, 3.3412888050079347, 4.36137056350708, 12.0, 8.28729248046875, 6.756756782531738, 5.016722202301025, 8.241758346557618, 9.677419662475586, 5.016722202301025, 7.109004974365234, 7.731958866119385, 6.976744174957275, 8.771929740905762, 4.504504680633545 ] }