ppo-LunarLander-v2 / results.json
CarlosGranados's picture
new_model: PPO model trained for 10 and 5000000 steps
d2e0a55 verified
raw
history blame contribute delete
165 Bytes
{"mean_reward": 297.47202961026994, "std_reward": 12.462012999163456, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-07-10T16:04:31.800197"}