PPO-LunarLander-v2 / results.json
Brainkite's picture
Longer trainning 3e6 timesteps
179116d
raw
history blame contribute delete
165 Bytes
{"mean_reward": 276.27411057442237, "std_reward": 20.795427502595313, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-03T10:29:03.648940"}