swaroop06
/

ppo-LunarLander-v2

Reinforcement Learning

stable-baselines3

deep-reinforcement-learning

Eval Results (legacy)

Model card Files Files and versions

PPO agent playing LunarLander-v2

This is a trained model of an PPO agent playing LunarLander-v2 for the Hugging Face Deep Reinforcement Learning Course (Unit 1).

Evaluation Results

Mean Reward: 285.50 +/- 15.20
Environment: LunarLander-v2
Algorithm: PPO
Library: stable-baselines3

Usage

Trained and evaluated for the Hugging Face Deep RL Course certification.

Downloads last month: 5

Video Preview

Reinforcement Learning

loading

Evaluation results

mean_reward on LunarLander-v2
self-reported

285.50 +/- 15.20