ppo-LunarLander-v2 / results.json
polyconnect's picture
PPO LunarLander-v2 trained agent - batchsize 32, total_timestaps 4M
03cb757 verified
raw
history blame contribute delete
165 Bytes
{"mean_reward": 276.55158739999996, "std_reward": 18.568109969404038, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-19T17:12:03.807524"}