ppo-LunarLander-v2 / results.json
cheremushkin's picture
1M iterations training
482d1d6
raw
history blame contribute delete
164 Bytes
{"mean_reward": 265.0016062990102, "std_reward": 18.081297403132503, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-03T21:59:59.686603"}