myv
/

ppo-LunarLander-v2

Reinforcement Learning

stable-baselines3

Eval Results (legacy)

Model card Files Files and versions

PPO Agent playing LunarLander-v3

Trained with Stable-Baselines3 PPO.

Results

Metric	Value
Mean reward	211.35 ± 106.91

Downloads last month: -

Video Preview

Reinforcement Learning

loading

Evaluation results

mean_reward on LunarLander-v3
self-reported

211.35 +/- 106.91