ppo-LunarLander-v2 / results.json
eikoenchine's picture
trained 1e7 timesteps
44de1a6
{"mean_reward": 294.8524473, "std_reward": 18.30344158934831, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-26T00:44:43.746201"}