中文
相关论文

相关论文: On the Convergence of Single-Timescale Actor-Criti…

200 篇论文

We introduce \texttt{OPO-CMDP}, the first policy optimization algorithm for stochastic Contextual Markov Decision Process (CMDPs) under general offline function approximation. Our approach achieves a high probability regret bound of…

机器学习 · 计算机科学 2026-02-17 Orin Levy , Aviv Rosenberg , Alon Cohen , Yishay Mansour

We propose a single time-scale actor-critic algorithm to solve the linear quadratic regulator (LQR) problem. A least squares temporal difference (LSTD) method is applied to the critic and a natural policy gradient method is used for the…

最优化与控制 · 数学 2022-06-07 Mo Zhou , Jianfeng Lu

Natural actor-critic (NAC) and its variants, equipped with the representation power of neural networks, have demonstrated impressive empirical success in solving Markov decision problems with large state spaces. In this paper, we present a…

机器学习 · 计算机科学 2022-06-03 Semih Cayci , Niao He , R. Srikant

This work revisits standard policy gradient methods used on restricted policy classes, which are known to get stuck in suboptimal critical points. We identify an important cause for this phenomenon to be that the policy gradient is itself…

机器学习 · 计算机科学 2026-05-12 Alex DeWeese , Guannan Qu

We study a structured bi-level optimization problem where the upper-level objective is a smooth function and the lower-level problem is policy optimization in a Markov decision process (MDP). The upper-level decision variable parameterizes…

机器学习 · 计算机科学 2026-04-23 Sihan Zeng , Sujay Bhatt , Sumitra Ganesh , Alec Koppel

We prove new upper and lower bounds for sample complexity of finding an $\epsilon$-optimal policy of an infinite-horizon average-reward Markov decision process (MDP) given access to a generative model. When the mixing time of the…

机器学习 · 计算机科学 2021-06-15 Yujia Jin , Aaron Sidford

Temporal-difference learning with gradient correction (TDC) is a two time-scale algorithm for policy evaluation in reinforcement learning. This algorithm was initially proposed with linear function approximation, and was later extended to…

机器学习 · 计算机科学 2021-10-29 Yue Wang , Shaofeng Zou , Yi Zhou

Actor-critic (AC) algorithms have been widely adopted in decentralized multi-agent systems to learn the optimal joint control policy. However, existing decentralized AC algorithms either do not preserve the privacy of agents or are not…

机器学习 · 计算机科学 2022-02-04 Ziyi Chen , Yi Zhou , Rongrong Chen , Shaofeng Zou

In this paper, we provide finite-sample convergence guarantees for an off-policy variant of the natural actor-critic (NAC) algorithm based on Importance Sampling. In particular, we show that the algorithm converges to a global optimal…

机器学习 · 计算机科学 2021-06-14 Sajad Khodadadian , Zaiwei Chen , Siva Theja Maguluri

Markov Decision Processes (MDPs) have been used to formulate many decision-making problems in science and engineering. The objective is to synthesize the best decision (action selection) policies to maximize expected rewards (minimize…

最优化与控制 · 数学 2015-07-08 Mahmoud El Chamie , Behcet Acikmese

The two-time scale nature of SAC, which is an actor-critic algorithm, is characterised by the fact that the critic estimate has not converged for the actor at any given time, but since the critic learns faster than the actor, it ensures…

A variety of theoretically-sound policy gradient algorithms exist for the on-policy setting due to the policy gradient theorem, which provides a simplified form for the gradient. The off-policy setting, however, has been less clear due to…

机器学习 · 计算机科学 2023-04-17 Eric Graves , Ehsan Imani , Raksha Kumaraswamy , Martha White

We study infinite-horizon robust Markov decision processes (MDPs) on continuous state spaces with structured rectangular ambiguity set. The proposed ambiguity set falls within the convex hull of unknown generating kernels. We utilize the…

最优化与控制 · 数学 2026-05-28 Mengmeng Li , Yifan Hu , Daniel Kuhn , Yan Li

This paper considers the problem of finding near-optimal Markovian randomized (MR) policies for finite-state-action, infinite-horizon, constrained risk-sensitive Markov decision processes (CRSMDPs). Constraints are in the form of standard…

最优化与控制 · 数学 2023-03-14 Uday Kumar M , Sanjay P Bhat , Veeraruna Kavitha , Nandyala Hemachandra

Dynamic optimization of mean and variance in Markov decision processes (MDPs) is a long-standing challenge caused by the failure of dynamic programming. In this paper, we propose a new approach to find the globally optimal policy for…

最优化与控制 · 数学 2023-02-28 Li Xia , Shuai Ma

We study policy optimization in Stackelberg mean field games (MFGs), a hierarchical framework for modeling the strategic interaction between a single leader and an infinitely large population of homogeneous followers. The objective can be…

机器学习 · 计算机科学 2025-11-27 Sihan Zeng , Benjamin Patrick Evans , Sujay Bhatt , Leo Ardon , Sumitra Ganesh , Alec Koppel

In this paper we consider the problem of computing an $\epsilon$-optimal policy of a discounted Markov Decision Process (DMDP) provided we can only access its transition function through a generative sampling model that given any…

最优化与控制 · 数学 2019-06-07 Aaron Sidford , Mengdi Wang , Xian Wu , Lin F. Yang , Yinyu Ye

We study the policy testing problem in discounted Markov decision processes (MDPs) in the fixed-confidence setting under a generative model with static sampling. The goal is to decide whether the value of a given policy exceeds a specified…

机器学习 · 统计学 2026-04-21 Kaito Ariu , Po-An Wang , Alexandre Proutiere , Kenshi Abe

The infinite horizon setting is widely adopted for problems of reinforcement learning (RL). These invariably result in stationary policies that are optimal. In many situations, finite horizon control problems are of interest and for such…

机器学习 · 计算机科学 2025-03-21 Soumyajit Guin , Shalabh Bhatnagar

In this paper, we study a mean-variance optimization problem in an infinite horizon discrete time discounted Markov decision process (MDP). The objective is to minimize the variance of system rewards with the constraint of mean performance.…

最优化与控制 · 数学 2017-08-24 Li Xia