Guru-Raja-124/ppo-LunarLander-v2

PPO LunarLander-v2

Stable-Baselines3 PPO agent trained on LunarLander-v2.

Evaluation

• Mean reward: 255.26
• Standard deviation: 22.00
• Certification score (mean_reward - std_reward): 233.25
• Evaluation episodes: 10
• Training timesteps: 1,000,000

Training

This model was trained using Stable-Baselines3 PPO with an MLP policy.