LunarLander / results.json
HatefulRock's picture
Trained RL Lunar lander using PPO architecture
23a7490
{"mean_reward": 294.83623972732215, "std_reward": 16.38865463048533, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-06T19:16:10.280079"}