{ "episodes": 50, "win_rate": 76.0, "avg_reward": 32.26594543457031, "reward_std": 3.5016987323760988, "avg_steps": 733.239990234375, "accuracy": 7.360834121704102, "smoothness": 0.22935977578163148, "all_rewards": [ 33.83667755126953, 36.04047393798828, 35.07730484008789, 34.72116470336914, 27.937835693359376, 32.390872955322269, 29.052644729614259, 37.128360748291019, 30.18748664855957, 27.669139862060548, 37.44949722290039, 31.926055908203126, 26.01382827758789, 33.449554443359378, 28.682157516479493, 33.873809814453128, 34.43446731567383, 22.25322723388672, 33.904144287109378, 36.419795989990237, 32.12141418457031, 30.48814582824707, 33.38386917114258, 36.123313903808597, 33.10539245605469, 27.102455139160158, 32.73951721191406, 33.180076599121097, 27.331743240356447, 36.580509185791019, 33.18541717529297, 33.63578414916992, 31.37065887451172, 33.787567138671878, 31.37879180908203, 33.99873352050781, 36.13295364379883, 23.137062072753908, 31.941749572753908, 34.80972671508789, 31.438879013061525, 35.06905746459961, 34.10222625732422, 33.41725158691406, 24.20496368408203, 34.69066619873047, 34.26713180541992, 33.3831787109375, 33.349544525146487, 31.391332626342775 ], "all_wins": [ 1, 1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1 ], "all_steps": [ 419, 689, 626, 695, 1001, 260, 1001, 694, 715, 1001, 798, 518, 1001, 841, 1001, 917, 527, 1001, 792, 956, 490, 666, 806, 662, 843, 1001, 801, 1001, 1001, 897, 647, 509, 606, 494, 316, 497, 773, 1001, 492, 505, 1001, 687, 564, 390, 1001, 711, 684, 925, 754, 484 ], "all_smoothness": [ 0.2260698825120926, 0.26938605308532717, 0.29566583037376406, 0.21936029195785523, 0.19958704710006715, 0.1518985480070114, 0.23203355073928834, 0.38198021054267886, 0.11990911513566971, 0.32546183466911318, 0.24443022906780244, 0.15109844505786897, 0.1709941178560257, 0.21879570186138154, 0.2829204201698303, 0.18386295437812806, 0.22048881649971009, 0.3107498586177826, 0.2439945936203003, 0.23007243871688844, 0.1524581015110016, 0.08495880663394928, 0.23275786638259889, 0.3941960036754608, 0.2636265456676483, 0.21932923793792725, 0.15263405442237855, 0.3049551844596863, 0.19486360251903535, 0.27845558524131777, 0.19779253005981446, 0.13475386798381806, 0.11494051665067673, 0.2387317568063736, 0.04907137528061867, 0.33622148633003237, 0.24011465907096864, 0.23912930488586427, 0.1320600062608719, 0.29890739917755129, 0.27595943212509158, 0.244807630777359, 0.33138081431388857, 0.24140112102031709, 0.16844779253005982, 0.2928061783313751, 0.17922692000865937, 0.2154448926448822, 0.19426336884498597, 0.10277693718671799 ], "all_accuracies": [ 9.433961868286133, 9.259259223937989, 8.474575996398926, 12.195121765136719, 4.8913044929504398, 13.88888931274414, 4.787233829498291, 6.134969234466553, 9.708738327026368, 3.08370041847229, 7.246376991271973, 13.1578950881958, 5.732483863830566, 7.633587837219238, 4.371584892272949, 8.130081176757813, 14.492753982543946, 3.0, 12.5, 5.524861812591553, 15.873015403747559, 12.34567928314209, 6.5789475440979, 4.149377822875977, 6.289308071136475, 6.122448921203613, 6.369426727294922, 4.32692289352417, 8.256880760192871, 7.352941036224365, 6.134969234466553, 14.70588207244873, 12.5, 16.94915199279785, 23.255813598632814, 5.586592197418213, 6.329113960266113, 5.223880767822266, 9.259259223937989, 7.246376991271973, 6.7164177894592289, 6.289308071136475, 6.993007183074951, 9.615385055541993, 6.666666507720947, 6.94444465637207, 13.88888931274414, 5.649717330932617, 9.174311637878418, 13.88888931274414 ] }