{ "episodes": 50, "win_rate": 64.0, "avg_reward": 30.912582397460939, "reward_std": 4.9194512367248539, "avg_steps": 852.0, "accuracy": 6.947779178619385, "smoothness": 0.25765591859817507, "all_rewards": [ 29.76290512084961, 32.19603729248047, 33.80971908569336, 34.03022384643555, 36.62681198120117, 26.442161560058595, 32.979095458984378, 15.8031587600708, 34.63829803466797, 31.734355926513673, 36.09659957885742, 35.67871856689453, 24.535675048828126, 21.729537963867189, 35.04241943359375, 28.94642448425293, 31.316822052001954, 22.627283096313478, 30.543516159057618, 36.964778900146487, 33.957489013671878, 35.33441162109375, 25.41167640686035, 34.366275787353519, 33.25990676879883, 29.39653778076172, 29.31793975830078, 35.250553131103519, 22.961355209350587, 26.73064422607422, 34.58393859863281, 33.36784744262695, 20.934711456298829, 31.605302810668947, 31.89141845703125, 32.527320861816409, 32.34486389160156, 35.00508499145508, 35.160335540771487, 21.588632583618165, 34.05859375, 28.34543800354004, 33.578468322753909, 33.92094039916992, 35.65074157714844, 33.436607360839847, 31.298622131347658, 34.43042755126953, 32.629051208496097, 21.779563903808595 ], "all_wins": [ 0, 1, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 0, 1, 0, 1, 0, 0, 1, 1, 1, 0, 1, 1, 0, 0, 1, 0, 0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 1, 1, 0 ], "all_steps": [ 1001, 825, 681, 812, 868, 1001, 975, 1001, 916, 750, 822, 667, 1001, 1001, 650, 1001, 811, 1001, 1001, 867, 597, 932, 1001, 637, 867, 1001, 1001, 797, 1001, 1001, 650, 730, 1001, 958, 842, 531, 454, 722, 868, 1001, 802, 1001, 583, 749, 796, 922, 1001, 722, 779, 1001 ], "all_smoothness": [ 0.27238860726356509, 0.2515987157821655, 0.23837657272815705, 0.29231172800064089, 0.3077859878540039, 0.3098265826702118, 0.2669755816459656, 0.3039603531360626, 0.2592756152153015, 0.1166594922542572, 0.32968205213546755, 0.2832297682762146, 0.11516182124614716, 0.2812967300415039, 0.27818137407302859, 0.2995487451553345, 0.1235726848244667, 0.3922847807407379, 0.32553550601005556, 0.391907274723053, 0.26107680797576907, 0.24561618268489839, 0.15193700790405274, 0.1986112892627716, 0.22569860517978669, 0.257758229970932, 0.3337976038455963, 0.2914414405822754, 0.06957083195447922, 0.36510857939720156, 0.2515636384487152, 0.26184505224227908, 0.3075138330459595, 0.17558099329471589, 0.13843950629234315, 0.17592640221118928, 0.15846110880374909, 0.3269174098968506, 0.2656049132347107, 0.23149214684963227, 0.262089341878891, 0.24753937125205995, 0.2050115168094635, 0.20121614634990693, 0.33979132771492007, 0.2910307049751282, 0.2865847647190094, 0.27025431394577029, 0.1639874130487442, 0.3266756236553192 ], "all_accuracies": [ 4.568527698516846, 8.064516067504883, 6.711409568786621, 9.615385055541993, 4.95049524307251, 6.106870174407959, 10.204081535339356, 13.513513565063477, 7.633587837219238, 14.925373077392579, 3.5460991859436037, 6.756756782531738, 13.043478012084961, 15.55555534362793, 8.196721076965332, 2.816901445388794, 9.523809432983399, 12.280701637268067, 9.090909004211426, 5.0, 11.764705657958985, 5.102040767669678, 5.590062141418457, 7.299270153045654, 11.627906799316407, 3.9823009967803957, 3.8277511596679689, 8.849557876586914, 10.588234901428223, 3.686635971069336, 5.882352828979492, 6.410256385803223, 13.95348834991455, 9.803921699523926, 10.526315689086914, 7.936507701873779, 17.85714340209961, 6.060606002807617, 5.319149017333984, 4.430379867553711, 5.15463924407959, 14.754097938537598, 8.771929740905762, 9.523809432983399, 5.0505051612854, 9.174311637878418, 4.918032646179199, 10.98901081085205, 8.928571701049805, 9.722222328186036 ] }