Implicit Policy for Reinforcement Learning

Yunhao Tang; Shipra Agrawal

Implicit Policy for Reinforcement Learning

Machine Learning 2019-02-05 v2 Artificial Intelligence Machine Learning

Authors: Yunhao Tang , Shipra Agrawal

Abstract

We introduce Implicit Policy, a general class of expressive policies that can flexibly represent complex action distributions in reinforcement learning, with efficient algorithms to compute entropy regularized policy gradients. We empirically show that, despite its simplicity in implementation, entropy regularization combined with a rich policy class can attain desirable properties displayed under maximum entropy reinforcement learning framework, such as robustness and multi-modality.

Keywords

policy gradient reinforcement learning multi-agent reinforcement learning

Cite

@article{arxiv.1806.06798,
  title  = {Implicit Policy for Reinforcement Learning},
  author = {Yunhao Tang and Shipra Agrawal},
  journal= {arXiv preprint arXiv:1806.06798},
  year   = {2019}
}

Related papers

View all related →