ppo-LunarLander-v2 / results.json
aspectcisco's picture
just finished this part 1 of the RL course, EZ Clap 228 mean reward, very ez indeed
578a015
raw
history blame contribute delete
163 Bytes
{"mean_reward": 136.0605593344986, "std_reward": 125.4769497634111, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-11-24T01:27:44.942195"}