ppo-LunarLander-v2 / results.json
sighmon's picture
Further 3 million steps. PPO LunarLander-v2 trained agent
56fe05b verified
raw
history blame contribute delete
158 Bytes
{"mean_reward": 275.0783856, "std_reward": 17.564916202211048, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-01-20T00:54:01.698684"}