ppo-LunarLander-v2 / results.json
dylwil3's picture
Attempt with KL cutoff, eval callback, and new hyperparams.
6c91cd8
raw
history blame contribute delete
164 Bytes
{"mean_reward": 245.38169347309622, "std_reward": 42.18764225825947, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-14T17:22:52.565712"}