PPO-LunarLander-v2_experiments / results.json

This is a simple PPO agent trained and evaluated for a free DRL course

a95d31b almost 3 years ago

164 Bytes

{"mean_reward": 264.1170068871596, "std_reward": 20.459064206473382, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-12T12:50:49.869815"}