ppo-LunarLander-v2 / results.json
Bhaclash's picture
Train model for 5 million timesteps
b044045
raw
history blame contribute delete
165 Bytes
{"mean_reward": 280.83004173848155, "std_reward": 21.032639440814673, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-17T22:12:47.408215"}