paper-with-me

홈 › Papers

On the Convergence and Sample Efficiency of Variance-Reduced Policy Gradient Method

2021-02-17 · NeurIPS 2021 12 · Junyu Zhang, Chengzhuo Ni, Zheng Yu, Csaba Szepesvari, Mengdi Wang

Policy gradient (PG) gives rise to a rich class of reinforcement learning (RL) methods. Recently, there has been an emerging trend to accelerate the existing PG methods such as REINFORCE by the \emph{variance reduction} techniques. However, all existing variance-reduced PG methods heavily rely on an uncheckable importance weight assumption made for every single iteration of the algorithms. In this paper, a simple gradient truncation mechanism is proposed to address this issue. Moreover, we design a Truncated Stochastic Incremental Variance-Reduced Policy Gradient (TSIVR-PG) method, which is able to maximize not only a cumulative sum of rewards but also a general utility function over a policy's long-term visiting distribution. We show an $\tilde{\mathcal{O}}(\epsilon^{-3})$ sample complexity for TSIVR-PG to find an $\epsilon$-stationary policy. By assuming the overparameterizaiton of policy and exploiting the hidden convexity of the problem, we further show that TSIVR-PG converges to global $\epsilon$-optimal policy with $\tilde{\mathcal{O}}(\epsilon^{-2})$ samples.

📄 PDF Abstract BibTeX arXiv:2102.08607

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

REINFORCE REINFORCE is a Monte Carlo variant of a policy gradient algorithm in reinforcement learning. The agent collects samples of an episode using its current policy, and uses it to…

Similar Papers 제목 키워드 기반

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

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 Fish…

Policy Gradient Methods

Variance-Reduced Off-Policy TDC Learning: Non-Asymptotic Convergence Analysis

2020-10-26 · NeurIPS 2020 12 · Shaocong Ma, Yi Zhou, Shaofeng Zou

Variance reduction techniques have been successfully applied to temporal-difference (TD) learning and help to improve the sample complexity in policy evaluation. However, the existing work applied variance reduction to e…

Variance Reduced Domain Randomization for Policy Gradient

2021-09-29 · Yuankun Jiang, Chenglin Li, Wenrui Dai, Junni Zou 외

By introducing randomness on environment parameters that fundamentally affect the dynamics, domain randomization (DR) imposes diversity to the policy trained by deep reinforcement learning, and thus improves its capabili…

Deep Reinforcement LearningPolicy Gradient Methods

Bregman Gradient Policy Optimization

2021-06-23 · ICLR 2022 4 · Feihu Huang, Shangqian Gao, Heng Huang

In the paper, we design a novel Bregman gradient policy optimization framework for reinforcement learning based on Bregman divergences and momentum techniques. Specifically, we propose a Bregman gradient policy optimizat…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)