aryasri15
/

ppo-scratch-LunarLander-v2

Reinforcement Learning

Eval Results (legacy)

Model card Files Files and versions

PPO from Scratch Agent playing LunarLander-v2

This model was trained as part of the Hugging Face Deep Reinforcement Learning Course.

Evaluation Result

Mean Reward: 220.0 +/- 10.0
Library: deep-rl-course
Environment: LunarLander-v2

Downloads last month: 15

Video Preview

Reinforcement Learning

loading

Evaluation results

mean_reward on LunarLander-v2
self-reported

220.0 +/- 10.0