| {"step": 1000, "overall": 0.535, "per_env": {"bulls_and_cows": {"mean_reward": 0.38, "n": 50}, "countdown": {"mean_reward": 0.36, "n": 50}, "zebra": {"mean_reward": 0.26, "n": 50}, "cryptarithm": {"mean_reward": 0.2, "n": 50}, "mastermind": {"mean_reward": 0.46, "n": 50}, "ordering": {"mean_reward": 0.7, "n": 50}, "shortest_path": {"mean_reward": 0.92, "n": 50}, "state_machine": {"mean_reward": 1.0, "n": 50}}} | |