PPO Agent Playing LunarLander-v2
This is a trained model of a PPO agent playing LunarLander-v2.
Hyperparameters
Evaluation results
- mean_reward on LunarLander-v2self-reported-231.53 +/- 121.00
![]() |
VOOZH | about |
This is a trained model of a PPO agent playing LunarLander-v2.