PPO Agent playing LunarLander-v2
This is a trained model of a PPO agent playing LunarLander-v2 using the stable-baselines3 library.
Solution-2024.11.11
A easy way to reach the score is to improve the training episodes.
model.learn(total_timesteps=3e6)
TODO: Add descriptions of other score improvement codes
- Downloads last month
- 0
Evaluation results
- mean_reward on LunarLander-v2self-reported284.96 +/- 27.66