ppo-LunarLander-v2 / results.json

trained agent with more steps and tuned parameters

1e4b65f verified 5 months ago

155 Bytes

{"mean_reward": 268.404671, "std_reward": 20.6337229199178, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-14T08:57:18.845918"}