PPO-LunarLander-v2 / results.json
chans's picture
initial model test
1e5f238
{"mean_reward": 248.15250348083993, "std_reward": 30.15496114152632, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-07T06:34:32.114860"}