Stochastic Variance-Reduced Policy Gradient
Abstract
In this paper, we propose a novel reinforcement- learning algorithm consisting in a stochastic variance-reduced version of policy gradient for solving Markov Decision Processes (MDPs). Stochastic variance-reduced gradient (SVRG) methods have proven to be very successful in supervised learning. However, their adaptation to policy gradient is not straightforward and needs to account for I) a non-concave objective func- tion; II) approximations in the full gradient com- putation; and III) a non-stationary sampling pro- cess. The result is SVRPG, a stochastic variance- reduced policy gradient algorithm that leverages on importance weights to preserve the unbiased- ness of the gradient estimate. Under standard as- sumptions on the MDP, we provide convergence guarantees for SVRPG with a convergence rate that is linear under increasing batch sizes. Finally, we suggest practical variants of SVRPG, and we empirically evaluate them on continuous MDPs.
Cite
@article{arxiv.1806.05618,
title = {Stochastic Variance-Reduced Policy Gradient},
author = {Matteo Papini and Damiano Binaghi and Giuseppe Canonaco and Matteo Pirotta and Marcello Restelli},
journal= {arXiv preprint arXiv:1806.05618},
year = {2018}
}