PPO Agent - LunarLander-v2
PPO reinforcement learning agent for LunarLander-v2.
Environment
- Environment: LunarLander-v2
- Algorithm: PPO
- Policy: MlpPolicy
Evaluation
Mean reward: 220.91
Standard deviation: 67.74
Certification reward: 153.17
Certification reward = mean reward - standard deviation.
Training
The PPO agent was trained for LunarLander and saved as a Stable-Baselines3 model.
- Downloads last month
- -
Evaluation results
- Mean reward on LunarLander-v2self-reported220.910
- Standard deviation on LunarLander-v2self-reported67.740
- Certification reward on LunarLander-v2self-reported153.170