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.
@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