PPO Agent playing LunarLander-v2
This is a trained model of a PPO agent playing LunarLander-v2 using stable-baselines3 and the Deep RL Course.
- Downloads last month
- 29
Evaluation results
- mean_reward on LunarLander-v2self-reported265.50 +/- 15.20
This is a trained model of a PPO agent playing LunarLander-v2 using stable-baselines3 and the Deep RL Course.