English

Policy Optimization with Second-Order Advantage Information

Machine Learning 2019-05-30 v2 Artificial Intelligence Machine Learning

Abstract

Policy optimization on high-dimensional continuous control tasks exhibits its difficulty caused by the large variance of the policy gradient estimators. We present the action subspace dependent gradient (ASDG) estimator which incorporates the Rao-Blackwell theorem (RB) and Control Variates (CV) into a unified framework to reduce the variance. To invoke RB, our proposed algorithm (POSA) learns the underlying factorization structure among the action space based on the second-order advantage information. POSA captures the quadratic information explicitly and efficiently by utilizing the wide & deep architecture. Empirical studies show that our proposed approach demonstrates the performance improvements on high-dimensional synthetic settings and OpenAI Gym's MuJoCo continuous control tasks.

Keywords

Cite

@article{arxiv.1805.03586,
  title  = {Policy Optimization with Second-Order Advantage Information},
  author = {Jiajin Li and Baoxiang Wang},
  journal= {arXiv preprint arXiv:1805.03586},
  year   = {2019}
}

Comments

International Joint Conference on Artificial Intelligence (IJCAI) 2018

R2 v1 2026-06-23T01:49:49.331Z