paper-with-me

홈 › Papers

An Improved Analysis of (Variance-Reduced) Policy Gradient and Natural Policy Gradient Methods

2022-11-15 · NeurIPS 2020 12 · Yanli Liu, Kaiqing Zhang, Tamer Başar, Wotao Yin

In this paper, we revisit and improve the convergence of policy gradient (PG), natural PG (NPG) methods, and their variance-reduced variants, under general smooth policy parametrizations. More specifically, with the Fisher information matrix of the policy being positive definite: i) we show that a state-of-the-art variance-reduced PG method, which has only been shown to converge to stationary points, converges to the globally optimal value up to some inherent function approximation error due to policy parametrization; ii) we show that NPG enjoys a lower sample complexity; iii) we propose SRVR-NPG, which incorporates variance-reduction into the NPG update. Our improvements follow from an observation that the convergence of (variance-reduced) PG and NPG methods can improve each other: the stationary convergence analysis of PG can be applied to NPG as well, and the global convergence analysis of NPG can help to establish the global convergence of (variance-reduced) PG methods. Our analysis carefully integrates the advantages of these two lines of works. Thanks to this improvement, we have also made variance-reduction for NPG possible, with both global convergence and an efficient finite-sample complexity.

📄 PDF Abstract BibTeX arXiv:2211.07937

Code (0)

등록된 구현이 없습니다.

Tasks

Policy Gradient Methods

Similar Papers 제목 키워드 기반

An Improved Convergence Analysis of Stochastic Variance-Reduced Policy Gradient

2019-05-29 · Pan Xu, Felicia Gao, Quanquan Gu

We revisit the stochastic variance-reduced policy gradient (SVRPG) method proposed by Papini et al. (2018) for reinforcement learning. We provide an improved convergence analysis of SVRPG and show that it can find an $\e…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

PAGE-PG: A Simple and Loopless Variance-Reduced Policy Gradient Method with Probabilistic Gradient Estimation

2022-02-01 · Matilde Gargiani, Andrea Zanelli, Andrea Martinelli, Tyler Summers 외

Despite their success, policy gradient methods suffer from high variance of the gradient estimate, which can result in unsatisfactory sample complexity. Recently, numerous variance-reduced extensions of policy gradient m…

Policy Gradient Methods

Stochastic Variance-Reduced Policy Gradient

2018-06-14 · ICML 2018 7 · Matteo Papini, Damiano Binaghi, Giuseppe Canonaco, Matteo Pirotta 외

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 gradien…

Reinforcement Learning

Variance-Reduced Off-Policy Memory-Efficient Policy Search

2020-09-14 · Daoming Lyu, Qi Qi, Mohammad Ghavamzadeh, Hengshuai Yao 외

Off-policy policy optimization is a challenging problem in reinforcement learning (RL). The algorithms designed for this problem often suffer from high variance in their estimators, which results in poor sample efficienc…

Reinforcement Learning (RL)Stochastic Optimization

Smoothed functional-based gradient algorithms for off-policy reinforcement learning: A non-asymptotic viewpoint

2021-01-06 · Nithia Vijayan, Prashanth L. A

We propose two policy gradient algorithms for solving the problem of control in an off-policy reinforcement learning (RL) context. Both algorithms incorporate a smoothed functional (SF) based gradient estimation scheme. …

Off-policy evaluationReinforcement Learning (RL)