Upload PPO MontezumaRevenge-v5 trained agent 1M timesteps, CNN 0.01 LR nsteps 4096
6fb822a
{"mean_reward": 0.0, "std_reward": 0.0, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-27T02:32:53.187579"} |
{"mean_reward": 0.0, "std_reward": 0.0, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-27T02:32:53.187579"} |