PPO LunarLander-v2 trained agent, 32 envs, 2M ep - version 02

5a53b32 verified about 2 years ago

165 Bytes

{"mean_reward": 268.22247000000004, "std_reward": 39.722492617305456, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-21T13:03:42.747706"}