ppo-LunarLander-v2 / results.json
mgfrantz's picture
Trained LunarLander-v2-PPO-0 for an additional 1e6 steps
788c358
raw
history blame
165 Bytes
{"mean_reward": 294.61028826670224, "std_reward": 18.686373085480827, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T17:23:03.824983"}