benballintyn
/

cnn-ppo-SpaceInvaders-v5_1

Reinforcement Learning

stable-baselines3

ALE/SpaceInvaders-v5

deep-reinforcement-learning

Eval Results (legacy)

Model card Files Files and versions

CNN-PPO Agent playing ALE/SpaceInvaders-v5

This is a trained model of a CNN-PPO agent playing ALE/SpaceInvaders-v5 using the stable-baselines3 library.

Usage (with Stable-baselines3)

TODO: Add your code

Downloads last month: 8

Video Preview

Reinforcement Learning

loading

Evaluation results

mean_reward on ALE/SpaceInvaders-v5
self-reported

143.50 +/- 73.04