English
Related papers

Related papers: Lower Bounds for Policy Iteration on Multi-action …

200 papers

We study an approach to policy selection for large relational Markov Decision Processes (MDPs). We consider a variant of approximate policy iteration (API) that replaces the usual value-function learning step with a learning step in policy…

Artificial Intelligence · Computer Science 2011-09-13 A. Fern , R. Givan , S. Yoon

In this paper we propose an on-line policy iteration (PI) algorithm for finite-state infinite horizon discounted dynamic programming, whereby the policy improvement operation is done on-line, only for the states that are encountered during…

Optimization and Control · Mathematics 2021-06-03 Dimitri Bertsekas

We consider the infinite-horizon discounted optimal control problem formalized by Markov Decision Processes. We focus on Policy Search algorithms, that compute an approximately optimal policy by following the standard Policy Iteration (PI)…

Artificial Intelligence · Computer Science 2013-06-04 Bruno Scherrer

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…

Machine Learning · Statistics 2021-10-26 Aymen Al Marjani , Aurélien Garivier , Alexandre Proutiere

We consider approximate dynamic programming in $\gamma$-discounted Markov decision processes and apply it to approximate planning with linear value-function approximation. Our first contribution is a new variant of Approximate Policy…

Machine Learning · Computer Science 2022-10-31 Gellért Weisz , András György , Tadashi Kozuno , Csaba Szepesvári

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…

Machine Learning · Statistics 2026-04-21 Kaito Ariu , Po-An Wang , Alexandre Proutiere , Kenshi Abe

Markov decision processes (MDPs) describe sequential decision-making processes; MDP policies return for every state in that process an advised action. Classical algorithms can efficiently compute policies that are optimal with respect to,…

Logic in Computer Science · Computer Science 2025-05-23 Roman Andriushchenko , Milan Češka , Sebastian Junges , Filip Macák

We study upper and lower bounds on the sample-complexity of learning near-optimal behaviour in finite-state discounted Markov Decision Processes (MDPs). For the upper bound we make the assumption that each action leads to at most two…

Machine Learning · Computer Science 2013-05-17 Tor Lattimore , Marcus Hutter

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…

Machine Learning · Computer Science 2024-05-01 Lakshmi Mandal , Chandrashekar Lakshminarayanan , Shalabh Bhatnagar

We investigate the problem of best policy identification in discounted linear Markov Decision Processes in the fixed confidence setting under a generative model. We first derive an instance-specific lower bound on the expected number of…

Machine Learning · Computer Science 2022-08-12 Jerome Taupin , Yassir Jedra , Alexandre Proutiere

The main goal of this paper is to apply the so-called policy iteration algorithm (PIA) for the long run average continuous control problem of piecewise deterministic Markov processes (PDMP's) taking values in a general Borel space and with…

Probability · Mathematics 2009-02-17 O. L. V. Costa , F. Dufour

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…

Data Structures and Algorithms · Computer Science 2010-03-18 John Fearnley

Policy iteration (PI) is a recursive process of policy evaluation and improvement for solving an optimal decision-making/control problem, or in other words, a reinforcement learning (RL) problem. PI has also served as the fundamental for…

Artificial Intelligence · Computer Science 2021-04-06 Jaeyoung Lee , Richard S. Sutton

We consider inexact policy iteration methods for large-scale infinite-horizon discounted MDPs with finite spaces, a variant of policy iteration where the policy evaluation step is implemented inexactly using an iterative solver for linear…

Optimization and Control · Mathematics 2024-04-10 Matilde Gargiani , Robin Sieber , Efe Balta , Dominic Liao-McPherson , John Lygeros

Memoryless and finite-memory policies offer a practical alternative for solving partially observable Markov decision processes (POMDPs), as they operate directly in the output space rather than in the high-dimensional belief space. However,…

Machine Learning · Computer Science 2025-12-15 Roy van Zuijlen , Duarte Antunes

This paper studies discounted Markov Decision Processes (MDPs) with finite sets of states and actions. Value iteration is one of the major methods for finding optimal policies. For each discount factor, starting from a finite number of…

Optimization and Control · Mathematics 2025-07-15 Eugene A. Feinberg , Gaojin He

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…

Machine Learning · Computer Science 2024-03-12 Navdeep Kumar , Yashaswini Murthy , Itai Shufaro , Kfir Y. Levy , R. Srikant , Shie Mannor

Consider the problem of approximating the optimal policy of a Markov decision process (MDP) by sampling state transitions. In contrast to existing reinforcement learning methods that are based on successive approximations to the nonlinear…

Machine Learning · Computer Science 2017-10-18 Mengdi Wang

Several recent works have proposed instance-dependent upper bounds on the number of episodes needed to identify, with probability $1-\delta$, an $\varepsilon$-optimal policy in finite-horizon tabular Markov Decision Processes (MDPs). These…

Machine Learning · Statistics 2023-11-13 Aymen Al-Marjani , Andrea Tirinzoni , Emilie Kaufmann

Unique Sink Orientations (USOs) are an appealing abstraction of several major optimization problems of applied mathematics such as for instance Linear Programming (LP), Markov Decision Processes (MDPs) or 2-player Turn Based Stochastic…

Discrete Mathematics · Computer Science 2015-01-12 Romain Hollanders , Balázs Gerencsér , Jean-Charles Delvenne , Raphaël M. Jungers