中文
相关论文

相关论文: The Smoothed Complexity of Policy Iteration for Ma…

200 篇论文

Deterministic Markov Decision Processes (DMDPs) are a mathematical framework for decision-making where the outcomes and future possible actions are deterministically determined by the current action taken. DMDPs can be viewed as a finite…

人工智能 · 计算机科学 2025-06-17 Ali Asadi , Krishnendu Chatterjee , Jakob de Raaij

We study policy iteration for infinite-horizon Markov decision processes. It has recently been shown policy iteration style algorithms have exponential lower bounds in a two player game setting. We extend these lower bounds to Markov…

数据结构与算法 · 计算机科学 2010-03-18 John Fearnley

We study the computational complexity of the infinite-horizon discounted-reward Markov Decision Problem (MDP) with a finite state space $|\mathcal{S}|$ and a finite action space $|\mathcal{A}|$. We show that any randomized algorithm needs a…

计算复杂性 · 计算机科学 2017-05-24 Yichen Chen , Mengdi Wang

Howard's Policy Iteration (HPI) is a classic algorithm for solving Markov Decision Problems (MDPs). HPI uses a "greedy" switching rule to update from any non-optimal policy to a dominating one, iterating until an optimal policy is found.…

人工智能 · 计算机科学 2025-05-05 Dibyangshu Mukherjee , Shivaram Kalyanakrishnan

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

We resolve the open question regarding the sample complexity of policy learning for maximizing the long-run average reward associated with a uniformly ergodic Markov decision process (MDP), assuming a generative model. In this context, the…

机器学习 · 计算机科学 2024-02-14 Shengbo Wang , Jose Blanchet , Peter Glynn

This paper studies parametric Markov decision processes (pMDPs), an extension to Markov decision processes (MDPs) where transitions probabilities are described by polynomials over a finite set of parameters. Fixing values for all parameters…

计算机科学中的逻辑 · 计算机科学 2019-04-03 Tobias Winkler , Sebastian Junges , Guillermo A. Pérez , Joost-Pieter Katoen

We present the first finite time global convergence analysis of policy gradient in the context of infinite horizon average reward Markov decision processes (MDPs). Specifically, we focus on ergodic tabular MDPs with finite state and action…

机器学习 · 计算机科学 2024-03-12 Navdeep Kumar , Yashaswini Murthy , Itai Shufaro , Kfir Y. Levy , R. Srikant , Shie Mannor

This article presents the complexity of reachability decision problems for parametric Markov decision processes (pMDPs), an extension to Markov decision processes (MDPs) where transitions probabilities are described by polynomials over a…

计算机科学中的逻辑 · 计算机科学 2020-09-29 Sebastian Junges , Joost-Pieter Katoen , Guillermo A. Pérez , Tobias Winkler

This paper addresses the challenge of solving Constrained Markov Decision Processes (CMDPs) with $d > 1$ constraints when the transition dynamics are unknown, but samples can be drawn from a generative model. We propose a model-based…

机器学习 · 计算机科学 2025-03-11 Max Buckley , Konstantinos Papathanasiou , Andreas Spanopoulos

We investigate the classical active pure exploration problem in Markov Decision Processes, where the agent sequentially selects actions and, from the resulting system trajectory, aims at identifying the best policy as fast as possible. We…

机器学习 · 统计学 2021-10-26 Aymen Al Marjani , Aurélien Garivier , Alexandre Proutiere

Given a Markov Decision Process (MDP) with $n$ states and a totalnumber $m$ of actions, we study the number of iterations needed byPolicy Iteration (PI) algorithms to converge to the optimal$\gamma$-discounted policy. We consider two…

最优化与控制 · 数学 2016-02-11 Bruno Scherrer

Policy iteration is a family of algorithms that are used to find an optimal policy for a given Markov Decision Problem (MDP). Simple Policy iteration (SPI) is a type of policy iteration where the strategy is to change the policy at exactly…

机器学习 · 计算机科学 2019-12-02 Sarthak Consul , Bhishma Dedhia , Kumar Ashutosh , Parthasarathi Khirwadkar

We study the sample complexity of learning an $\varepsilon$-optimal policy in an average-reward Markov decision process (MDP) under a generative model. For weakly communicating MDPs, we establish the complexity bound…

机器学习 · 计算机科学 2025-02-25 Matthew Zurek , Yudong Chen

We study regret minimization for infinite-horizon average-reward Markov Decision Processes (MDPs) under cost constraints. We start by designing a policy optimization algorithm with carefully designed action-value estimator and bonus term,…

机器学习 · 计算机科学 2022-02-02 Liyu Chen , Rahul Jain , Haipeng Luo

Recent advances have significantly improved our understanding of the sample complexity of learning in average-reward Markov decision processes (AMDPs) under the generative model. However, much less is known about the constrained…

机器学习 · 计算机科学 2025-09-23 Yukuan Wei , Xudong Li , Lin F. Yang

While learning in an unknown Markov Decision Process (MDP), an agent should trade off exploration to discover new information about the MDP, and exploitation of the current knowledge to maximize the reward. Although the agent will…

机器学习 · 计算机科学 2020-07-16 Evrard Garcelon , Mohammad Ghavamzadeh , Alessandro Lazaric , Matteo Pirotta

The online Markov decision process (MDP) is a generalization of the classical Markov decision process that incorporates changing reward functions. In this paper, we propose practical online MDP algorithms with policy iteration and…

机器学习 · 计算机科学 2015-10-16 Yao Ma , Hao Zhang , Masashi Sugiyama

A basic model in sequential decision making is the Markov decision process (MDP), which is extended to Robust MDPs (RMDPs) by allowing uncertainty in transition probabilities and optimizing against the worst-case transition probabilities…

计算复杂性 · 计算机科学 2026-05-11 Ali Asadi , Krishnendu Chatterjee , Alipasha Montaseri , Ali Shafiee

We study robust Markov decision processes (RMDPs) with general policy parameterization under s-rectangular and non-rectangular uncertainty sets. Prior work is largely limited to tabular policies, and hence either lacks sample complexity…

机器学习 · 计算机科学 2026-02-13 Anirudh Satheesh , Ziyi Chen , Furong Huang , Heng Huang
‹ 上一页 1 2 3 10 下一页 ›