edbeeching
/

atari_2B_atari_pong_1111

Reinforcement Learning

deep-reinforcement-learning

PongNoFrameskip-v4

Model card Files Files and versions Metrics Training metrics Community

Edit model card

A(n) APPO model trained on the atari_pong environment. This model was trained using Sample Factory 2.0: https://github.com/alex-petrenko/sample-factory

Downloads last month: 6

Video Preview

Reinforcement Learning

loading

Evaluation results

mean_reward on atari_pong
self-reported

20.95 +/- 0.22

View on Papers With Code