ppo-LunarLander-v2 Agent playing LunarLander-v2
This is a trained model of a ppo-LunarLander-v2 agent playing LunarLander-v2 using the stable-baselines3 library. Trained for the Hugging Face Deep Reinforcement Learning Course.
Evaluation Results
- Mean Reward: 275.81
- Std Reward: 26.46
- Score (Mean - Std): 249.35
- Downloads last month
- -
Evaluation results
- mean_reward on LunarLander-v2self-reported275.81 +/- 26.46