ppo-LunarLander-v2 / results.json
grunty's picture
Reinforcement learning class 1
dcb879c
raw
history blame contribute delete
164 Bytes
{"mean_reward": 225.4527629114216, "std_reward": 14.855871410997137, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-13T22:59:13.433556"}