ppo-LunarLander-v2 / results.json
stochastic's picture
trying out clip
91b1c14
{"mean_reward": -66.85736721422313, "std_reward": 139.52567140425782, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-23T16:08:13.023523"}