/humanoid-run-ppo

Code for the paper "Learning Humanoid Robot Running Skills through Proximal Policy Optimization"

Primary LanguageC++

humanoid-run-ppo

Code for the paper "Learning Humanoid Robot Running Skills through Proximal Policy Optimization"

In this repository, we release the learning agent's code to give details about our MDP and training procedure. If you would like to check the logs, photos, videos and results, we refer to: http://tiny.cc/vzc5cz

If you use this work, please cite the paper.