ppo-LunarLander-v2 / results.json
eelang's picture
First implementation. mean_reward=235.67 +/- 43.70256071321255
0b88b27
raw
history blame contribute delete
No virus
165 Bytes
{"mean_reward": 231.47739719999998, "std_reward": 31.956874643209254, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-08-01T16:32:17.430688"}