{ "episodes": 50, "win_rate": 0.0, "avg_reward": 40.16785430908203, "reward_std": 7.106827735900879, "avg_steps": 1001.0, "accuracy": 6.128191947937012, "smoothness": 0.3178701400756836, "all_rewards": [ 44.23982238769531, 44.41929626464844, 50.5387077331543, 41.364776611328128, 40.64315414428711, 36.98855972290039, 45.52259063720703, 32.28818130493164, 40.60206985473633, 13.393214225769043, 46.72441864013672, 45.44512939453125, 48.89778137207031, 32.53654861450195, 38.2696418762207, 41.644073486328128, 44.94176483154297, 36.68928909301758, 27.948291778564454, 32.70029067993164, 42.50714874267578, 42.901119232177737, 37.768898010253909, 43.98725509643555, 43.3924446105957, 32.62588882446289, 29.09087371826172, 38.50340270996094, 43.28812026977539, 45.56755828857422, 39.18561935424805, 40.303863525390628, 26.10457420349121, 43.901248931884769, 43.82325744628906, 20.619306564331056, 40.033756256103519, 45.21401596069336, 43.243961334228519, 42.95314025878906, 45.78666305541992, 39.08649826049805, 40.505008697509769, 45.39446258544922, 42.76457977294922, 45.82875061035156, 41.99637985229492, 45.85948181152344, 42.7558708190918, 47.60210037231445 ], "all_wins": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "all_steps": [ 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001, 1001 ], "all_smoothness": [ 0.29673323035240176, 0.3481021821498871, 0.29813671112060549, 0.2977076470851898, 0.19928587973117829, 0.3044113516807556, 0.32463330030441286, 0.3067784011363983, 0.3737984001636505, 0.3944458067417145, 0.237016960978508, 0.32888129353523257, 0.22614799439907075, 0.38086581230163576, 0.2946653366088867, 0.33101892471313479, 0.2793067395687103, 0.3955191969871521, 0.32704412937164309, 0.32812219858169558, 0.3494020700454712, 0.2875537872314453, 0.3619532287120819, 0.324697345495224, 0.2869596481323242, 0.3651787042617798, 0.4248327612876892, 0.42811745405197146, 0.28044354915618899, 0.27219298481941225, 0.37033647298812868, 0.3443385362625122, 0.37286844849586489, 0.27209463715553286, 0.2415187954902649, 0.37060898542404177, 0.29973432421684267, 0.2572852671146393, 0.2963121235370636, 0.32517412304878237, 0.3249203562736511, 0.3284027576446533, 0.4204712510108948, 0.31377658247947695, 0.3238716721534729, 0.3351607322692871, 0.24872542917728425, 0.2671131193637848, 0.3201431632041931, 0.20667801797389985 ], "all_accuracies": [ 6.435643672943115, 3.8922154903411867, 6.849315166473389, 6.153846263885498, 7.4285712242126469, 5.670103073120117, 6.9892473220825199, 7.299270153045654, 3.4810125827789308, 25.0, 11.538461685180664, 7.558139324188232, 8.474575996398926, 3.3333332538604738, 6.818181991577148, 6.976744174957275, 5.65217399597168, 3.6231884956359865, 14.0625, 6.569343090057373, 5.405405521392822, 10.909090995788575, 5.729166507720947, 17.283950805664064, 6.666666507720947, 4.0723981857299809, 2.6936028003692629, 3.055555582046509, 7.514451026916504, 6.25, 4.400000095367432, 7.142857074737549, 11.594202995300293, 5.485231876373291, 7.650273323059082, 6.25, 6.703910827636719, 4.761904716491699, 5.909090995788574, 7.017543792724609, 7.103825092315674, 6.25, 4.824561595916748, 5.118110179901123, 5.911330223083496, 6.25, 11.818181991577149, 10.0, 4.97925329208374, 8.379888534545899 ] }