PPO_Lander_original_data / results.json
slarionne's picture
Upload PPO LunarLander-v2 trained agent with original parameters
29a54b2
{"mean_reward": 220.1449676963157, "std_reward": 76.20268939491676, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-08-14T19:32:20.505909"}