hf-drl-unit1 / results.json
dweeb's picture
PPO LunarLander-v2 trained agent for unit 1
5017332
{"mean_reward": -60.388064099999994, "std_reward": 147.37441164432082, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-24T23:45:30.225177"}