sevlabr's picture
Upload PPO agent trained in LunarLander-v2 for Unit 1 Deep-RL Course. Epochs: 500k, Mean Reward: 192 +/- 75
64b3873
{"mean_reward": 222.00436998752897, "std_reward": 55.657747481455104, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-19T21:52:11.387606"}