[ { "update": 0, "mean_ep_reward": 0.974999999627471, "credit_auc": 0.4739525604078918, "n_reward_actions": 13 }, { "update": 1, "mean_ep_reward": 1.0, "credit_auc": 0.3764367816091954, "n_reward_actions": 12 }, { "update": 2, "mean_ep_reward": 1.0, "credit_auc": 0.3994252873563218, "n_reward_actions": 12 }, { "update": 3, "mean_ep_reward": 1.2416666665424902, "credit_auc": 0.29723837209302323, "n_reward_actions": 16 }, { "update": 4, "mean_ep_reward": 1.0833333333333333, "credit_auc": 0.3329638661050765, "n_reward_actions": 13 }, { "update": 5, "mean_ep_reward": 1.1666666666666667, "credit_auc": 0.3879025598678778, "n_reward_actions": 14 }, { "update": 6, "mean_ep_reward": 0.8916666662941376, "credit_auc": 0.29643136233394113, "n_reward_actions": 11 }, { "update": 7, "mean_ep_reward": 1.0583333329608042, "credit_auc": 0.29686209744013214, "n_reward_actions": 14 }, { "update": 8, "mean_ep_reward": 1.1666666666666667, "credit_auc": 0.29603633360858794, "n_reward_actions": 14 }, { "update": 9, "mean_ep_reward": 1.0749999998758237, "credit_auc": 0.3226672171758877, "n_reward_actions": 14 }, { "update": 10, "mean_ep_reward": 1.224999999627471, "credit_auc": 0.45875726744186046, "n_reward_actions": 16 }, { "update": 11, "mean_ep_reward": 1.0499999995032947, "credit_auc": 0.2667217175887696, "n_reward_actions": 14 }, { "update": 12, "mean_ep_reward": 1.0833333333333333, "credit_auc": 0.4216360008867214, "n_reward_actions": 13 }, { "update": 13, "mean_ep_reward": 0.8999999997516474, "credit_auc": 0.29747330033862984, "n_reward_actions": 11 }, { "update": 14, "mean_ep_reward": 1.1666666666666667, "credit_auc": 0.3914120561519405, "n_reward_actions": 14 } ]