{ "phase": "done", "cycles_done": 0, "history": [ { "phase": "train_A", "trained": "ALE/Breakout-v5", "A": 1.7, "status": "committed", "base": "-inf", "best": 2.4 }, { "phase": "train_A", "trained": "ALE/Breakout-v5", "A": 3.3, "status": "committed", "base": 1.8, "best": 3.3 }, { "phase": "train_A", "trained": "ALE/Breakout-v5", "A": 16.2, "status": "committed", "base": 4.6, "best": 12.3 }, { "phase": "train_A", "trained": "ALE/Breakout-v5", "A": 19.3, "status": "committed", "base": 13.9, "best": 16.5 }, { "phase": "train_A", "trained": "ALE/Breakout-v5", "A": 18.6, "status": "rejected_kept_base", "base": 19.3, "best": 19.3 } ] }