paper-with-me

Papers

Variance-Reduced Conservative Policy Iteration

2022-12-12 · Naman Agarwal, Brian Bullins, Karan Singh

We study the sample complexity of reducing reinforcement learning to a sequence of empirical risk minimization problems over the policy space. Such reductions-based algorithms exhibit local convergence in the function space, as opposed to the parameter space for policy gradient algorithms, and thus are unaffected by the possibly non-linear or discontinuous parameterization of the policy class. We propose a variance-reduced variant of Conservative Policy Iteration that improves the sample complexity of producing a $\varepsilon$-functional local optimum from $O(\varepsilon^{-4})$ to $O(\varepsilon^{-3})$. Under state-coverage and policy-completeness assumptions, the algorithm enjoys $\varepsilon$-global optimality after sampling $O(\varepsilon^{-2})$ times, improving upon the previously established $O(\varepsilon^{-3})$ sample requirement.

📄 PDF Abstract BibTeX arXiv:2212.06283

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

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)

Momentum-Based Policy Gradient with Second-Order Information

2022-05-17 · Saber Salehkaleybar, Sadegh Khorasani, Negar Kiyavash, Niao He 외

Variance-reduced gradient estimators for policy gradient methods have been one of the main focus of research in the reinforcement learning in recent years as they allow acceleration of the estimation process. We propose …

Policy Gradient Methods

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 외

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} …

Reinforcement Learning (RL)

Cautious Actor-Critic

2021-07-12 · Lingwei Zhu, Toshinori Kitamura, Takamitsu Matsubara

The oscillating performance of off-policy learning and persisting errors in the actor-critic (AC) setting call for algorithms that can conservatively learn to suit the stability-critical applications better. In this pape…

continuous-controlContinuous Control

Stochastic Dimension-reduced Second-order Methods for Policy Optimization

2023-01-28 · Jinsong Liu, Chenghan Xie, Qi Deng, Dongdong Ge 외

In this paper, we propose several new stochastic second-order algorithms for policy optimization that only require gradient and Hessian-vector product in each iteration, making them computationally efficient and comparab…

Policy Gradient MethodsSecond-order methods