yjhong89/TRPO-GAE

Trust Region Policy Optimization with Generalized Advantage Estimator

TRPO with GAE

Tensorflow implementation of TRPO(Trust Region Policy Optimization) with GAE(Generalized Advantage Estimator) on mujoco

Reference

• Paper
  • Trust Region Policy Optimization
  • Generalized Advantage Estimator
• Code
  • https://github.com/kvfrans/parallel-trpo
  • https://github.com/wojzaremba/trpo