English
Related papers

Related papers: Strong Polynomiality of the Value Iteration Algori…

200 papers

We propose an algorithm for deterministic continuous Markov Decision Processes with sparse rewards that computes the optimal policy exactly with no dependency on the size of the state space. The algorithm has time complexity of $O( |R|^3…

Machine Learning · Computer Science 2018-05-21 Joshua R. Bertram , Peng Wei

Reinforcement learning considers the problem of finding policies that maximize an expected cumulative reward in a Markov decision process with unknown transition probabilities. In this paper we consider the problem of finding optimal…

Machine Learning · Computer Science 2020-10-19 Santiago Paternain , Juan Andres Bazerque , Alejandro Ribeiro

At the working heart of policy iteration algorithms commonly used and studied in the discounted setting of reinforcement learning, the policy evaluation step estimates the value of states with samples from a Markov reward process induced by…

Machine Learning · Computer Science 2021-03-04 Falcon Z. Dai , Matthew R. Walter

In this paper, we settle the sampling complexity of solving discounted two-player turn-based zero-sum stochastic games up to polylogarithmic factors. Given a stochastic game with discount factor $\gamma\in(0,1)$ we provide an algorithm that…

Machine Learning · Computer Science 2019-08-30 Aaron Sidford , Mengdi Wang , Lin F. Yang , Yinyu Ye

Solving partially observable Markov decision processes (POMDPs) typically requires reasoning about the values of exponentially many state beliefs. Towards practical performance, state-of-the-art solvers use value bounds to guide this…

Artificial Intelligence · Computer Science 2025-02-11 Merlijn Krale , Wietze Koops , Sebastian Junges , Thiago D. Simão , Nils Jansen

Partially observable Markov decision processes (POMDPs) have recently become popular among many AI researchers because they serve as a natural model for planning under uncertainty. Value iteration is a well-known algorithm for finding…

Artificial Intelligence · Computer Science 2011-06-02 N. L. Zhang , W. Zhang

We study the problem of reinforcement learning in infinite-horizon discounted linear Markov decision processes (MDPs), and propose the first computationally efficient algorithm achieving rate-optimal regret guarantees in this setting. Our…

Machine Learning · Computer Science 2026-03-16 Antoine Moulin , Gergely Neu , Luca Viano

We consider Markov Decision Processes (MDPs) where the rewards are unknown and may change in an adversarial manner. We provide an algorithm that achieves state-of-the-art regret bound of $O( \sqrt{\tau (\ln|S|+\ln|A|)T}\ln(T))$, where $S$…

Machine Learning · Computer Science 2019-05-28 Adrian Rivera Cardoso , He Wang , Huan Xu

We consider the problem: is the optimal expected total reward to reach a goal state in a partially observable Markov decision process (POMDP) below a given threshold? We tackle this -- generally undecidable -- problem by computing…

Artificial Intelligence · Computer Science 2022-01-24 Alexander Bork , Joost-Pieter Katoen , Tim Quatmann

Suppose an agent is in a (possibly unknown) Markov Decision Process in the absence of a reward signal, what might we hope that an agent can efficiently learn to do? This work studies a broad class of objectives that are defined solely as…

Machine Learning · Computer Science 2019-01-29 Elad Hazan , Sham M. Kakade , Karan Singh , Abby Van Soest

In this paper, we provide a novel algorithm for solving planning and learning problems of Markov decision processes. The proposed algorithm follows a policy iteration-type update by using a rank-one approximation of the transition…

Optimization and Control · Mathematics 2025-10-23 Arman Sharifi Kolarijani , Tolga Ok , Peyman Mohajerin Esfahani , Mohamad Amin Sharif Kolarijani

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…

Computational Complexity · Computer Science 2026-05-11 Ali Asadi , Krishnendu Chatterjee , Alipasha Montaseri , Ali Shafiee

A standard objective in partially-observable Markov decision processes (POMDPs) is to find a policy that maximizes the expected discounted-sum payoff. However, such policies may still permit unlikely but highly undesirable outcomes, which…

Artificial Intelligence · Computer Science 2017-01-31 Krishnendu Chatterjee , Petr Novotný , Guillermo A. Pérez , Jean-François Raskin , Đorđe Žikelić

We consider the Monte-Carlo first visit algorithm, of which the goal is to find the optimal control in a Markov decision process with finite state space and finite number of possible actions. We show its convergence when the discount factor…

Probability · Mathematics 2025-09-23 Sylvain Delattre , Nicolas Fournier

General purpose intelligent learning agents cycle through (complex,non-MDP) sequences of observations, actions, and rewards. On the other hand, reinforcement learning is well-developed for small finite state Markov Decision Processes…

Artificial Intelligence · Computer Science 2009-12-30 Marcus Hutter

Euclidean Markov decision processes are a powerful tool for modeling control problems under uncertainty over continuous domains. Finite state imprecise, Markov decision processes can be used to approximate the behavior of these infinite…

Artificial Intelligence · Computer Science 2020-06-29 Manfred Jaeger , Giorgio Bacci , Giovanni Bacci , Kim Guldstrand Larsen , Peter Gjøl Jensen

The most relevant problems in discounted reinforcement learning involve estimating the mean of a function under the stationary distribution of a Markov reward process, such as the expected return in policy evaluation, or the policy gradient…

Machine Learning · Computer Science 2023-04-17 Alberto Maria Metelli , Mirco Mutti , Marcello Restelli

We study infinite horizon control of continuous-time non-linear branching processes with almost sure extinction for general (positive or negative) discount. Our main goal is to study the link between infinite horizon control of these…

Probability · Mathematics 2016-07-28 Julien Claisse , Nicolas Champagnat

Interpretability of reinforcement learning policies is essential for many real-world tasks but learning such interpretable policies is a hard problem. Particularly rule-based policies such as decision trees and rules lists are difficult to…

Artificial Intelligence · Computer Science 2024-02-15 Daniël Vos , Sicco Verwer

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.…

Systems and Control · Electrical Eng. & Systems 2023-02-08 Arash Bahari Kordabad , Mario Zanon , Sebastien Gros