中文
相关论文

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

200 篇论文

This paper shows that the optimal policy and value functions of a Markov Decision Process (MDP), either discounted or not, can be captured by a finite-horizon undiscounted Optimal Control Problem (OCP), even if based on an inexact model.…

系统与控制 · 电气工程与系统科学 2023-02-08 Arash Bahari Kordabad , Mario Zanon , Sebastien Gros

Multi-agent reinforcement learning (MARL) has attracted much research attention recently. However, unlike its single-agent counterpart, many theoretical and algorithmic aspects of MARL have not been well-understood. In this paper, we study…

机器学习 · 计算机科学 2021-12-08 Siliang Zeng , Tianyi Chen , Alfredo Garcia , Mingyi Hong

We derive a novel asymptotic problem-dependent lower-bound for regret minimization in finite-horizon tabular Markov Decision Processes (MDPs). While, similar to prior work (e.g., for ergodic MDPs), the lower-bound is the solution to an…

机器学习 · 计算机科学 2021-06-25 Andrea Tirinzoni , Matteo Pirotta , Alessandro Lazaric

Constrained Markov Decision Process (CMDP) is a natural framework for reinforcement learning tasks with safety constraints, where agents learn a policy that maximizes the long-term reward while satisfying the constraints on the long-term…

人工智能 · 计算机科学 2018-02-20 Qingkai Liang , Fanyu Que , Eytan Modiano

We build on a recently introduced geometric interpretation of Markov Decision Processes (MDPs) to analyze classical MDP-solving algorithms: Value Iteration (VI) and Policy Iteration (PI). First, we develop a geometry-based analytical…

机器学习 · 计算机科学 2025-03-07 Arsenii Mustafin , Aleksei Pakharev , Alex Olshevsky , Ioannis Ch. Paschalidis

Markov decision processes (MDPs) are the defacto frame-work for sequential decision making in the presence ofstochastic uncertainty. A classical optimization criterion forMDPs is to maximize the expected discounted-sum pay-off, which…

人工智能 · 计算机科学 2020-02-28 Tomas Brazdil , Krishnendu Chatterjee , Petr Novotny , Jiri Vahala

We introduce and study constrained Markov Decision Processes (cMDPs) with anytime constraints. An anytime constraint requires the agent to never violate its budget at any point in time, almost surely. Although Markovian policies are no…

机器学习 · 计算机科学 2024-06-14 Jeremy McMahan , Xiaojin Zhu

We study policy optimization for Markov decision processes (MDPs) with multiple reward value functions, which are to be jointly optimized according to given criteria such as proportional fairness (smooth concave scalarization), hard…

机器学习 · 计算机科学 2022-10-19 Ruida Zhou , Tao Liu , Dileep Kalathil , P. R. Kumar , Chao Tian

In this work, we consider a cooperative multi-agent Markov decision process (MDP) involving m agents. At each decision epoch, all the m agents independently select actions in order to maximize a common long-term objective. In the policy…

机器学习 · 计算机科学 2024-05-01 Lakshmi Mandal , Chandrashekar Lakshminarayanan , Shalabh Bhatnagar

Public health organizations face the problem of dispensing treatments (i.e., vaccines, antibiotics, and others) to groups of affected populations through "points-of-dispensing" (PODs) during emergency situations, typically in the presence…

最优化与控制 · 数学 2021-05-04 Yijia Wang , Daniel R. Jiang

Value iteration is a well-known method of solving Markov Decision Processes (MDPs) that is simple to implement and boasts strong theoretical convergence guarantees. However, the computational cost of value iteration quickly becomes…

机器学习 · 计算机科学 2021-07-26 Guanting Chen , Johann Demetrio Gaebler , Matt Peng , Chunlin Sun , Yinyu Ye

Reinforcement learning with multiple, potentially conflicting objectives is pervasive in real-world applications, while this problem remains theoretically under-explored. This paper tackles the multi-objective reinforcement learning (MORL)…

机器学习 · 计算机科学 2024-05-10 Tianchen Zhou , FNU Hairi , Haibo Yang , Jia Liu , Tian Tong , Fan Yang , Michinari Momma , Yan Gao

In this paper, we propose a distributed off-policy actor critic method to solve multi-agent reinforcement learning problems. Specifically, we assume that all agents keep local estimates of the global optimal policy parameter and update…

机器学习 · 计算机科学 2019-03-25 Yan Zhang , Michael M. Zavlanos

We study the problem of learning policy of an infinite-horizon, discounted cost, Markov decision process (MDP) with a large number of states. We compute the actions of a policy that is nearly as good as a policy chosen by a suitable oracle…

机器学习 · 计算机科学 2019-09-02 Masoud Badiei Khuzani , Varun Vasudevan , Hongyi Ren , Lei Xing

Actor-critic methods are widely used in offline reinforcement learning practice, but are not so well-understood theoretically. We propose a new offline actor-critic algorithm that naturally incorporates the pessimism principle, leading to…

机器学习 · 计算机科学 2021-08-20 Andrea Zanette , Martin J. Wainwright , Emma Brunskill

We consider a Markov decision process (MDP) in which actions prescribed by the controller are executed by a separate actuator, which may behave adversarially. At each time step, the controller selects and transmits an action to the…

信息论 · 计算机科学 2025-01-29 Edoardo David Santi , Gongpu Chen , Deniz Gündüz , Asaf Cohen

We consider the problem of constrained Markov decision process (CMDP) in continuous state-actions spaces where the goal is to maximize the expected cumulative reward subject to some constraints. We propose a novel Conservative Natural…

机器学习 · 计算机科学 2024-05-20 Qinbo Bai , Amrit Singh Bedi , Vaneet Aggarwal

In this paper, we study the convergence properties of off-policy policy improvement algorithms with state-action density ratio correction under function approximation setting, where the objective function is formulated as a max-max-min…

机器学习 · 计算机科学 2022-02-15 Jiawei Huang , Nan Jiang

We study policy optimization for infinite-horizon, discounted constrained Markov decision processes (CMDPs). While existing theoretical guarantees typically hold for the mixture policy, deploying such a policy is computationally and memory…

机器学习 · 计算机科学 2026-05-13 Michael Lu , Max Qiushi Lin , Mo Chen , Sharan Vaswani

This paper studies policy optimization algorithms for multi-agent reinforcement learning. We begin by proposing an algorithm framework for two-player zero-sum Markov Games in the full-information setting, where each iteration consists of a…

机器学习 · 计算机科学 2022-07-26 Runyu Zhang , Qinghua Liu , Huan Wang , Caiming Xiong , Na Li , Yu Bai