PPO Agent Playing LunarLander-v2

This is a trained model of a PPO agent playing LunarLander-v2.

Mean Reward

13.46 +/- 125.62

Hyperparameters

{'env_id': 'LunarLander-v2', 'repo_id': 'Tass-k/ppo-LunarLander-v2'}
Downloads last month
20
Video Preview
loading

Evaluation results