Rebixa
/

ppo-LunarLander-v2

Reinforcement Learning

deep-reinforcement-learning

custom-implementation

Eval Results (legacy)

Model card Files Files and versions

PPO Agent Playing LunarLander-v2

This is a trained model of a PPO agent playing LunarLander-v2. Trained from scratch using PyTorch (CleanRL-style implementation).

Results

Mean Reward: 97.67 +/- 91.15

Downloads last month: -; Downloads are not tracked for this model. How to track

Video Preview

Reinforcement Learning

loading

Evaluation results

mean_reward on LunarLander-v2
self-reported

97.67 +/- 91.15