JOSEFSUSON
/

ppo-Pendulum-v1-Excellence

Reinforcement Learning

stable-baselines3

deep-reinforcement-learning-course

Eval Results (legacy)

Model card Files Files and versions

PPO Agent playing Pendulum-v1

This is a trained model of a PPO agent playing Pendulum-v1 using the stable-baselines3 library.

Evaluation Results

Mean Reward: -275.82 +/- 139.80
Environment: Pendulum-v1
Framework: Stable-Baselines3 (PPO)

Downloads last month: -

Video Preview

Reinforcement Learning

loading

Evaluation results

mean_reward on Pendulum-v1
self-reported

-275.82 +/- 139.80