PPO-LunarLander-v2 / results.json
npit's picture
Proper training for HF DRL course unit1
92710c6
{"mean_reward": 259.73033603729806, "std_reward": 24.89968271604689, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-13T19:29:37.688414"}