English
Related papers

Related papers: Exponential Lower Bounds For Policy Iteration

200 papers

We consider a discrete-time Markov decision process with Borel state and action spaces. The performance criterion is to maximize a total expected {utility determined by unbounded return function. It is shown the existence of optimal…

Probability · Mathematics 2018-10-08 François Dufour , Alexandre Genadot

Optimal policies in standard MDPs can be obtained using either value iteration or policy iteration. However, in the case of zero-sum Markov games, there is no efficient policy iteration algorithm; e.g., it has been shown that one has to…

Machine Learning · Computer Science 2023-10-31 Anna Winnicki , R. Srikant

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,…

Machine Learning · Computer Science 2022-02-02 Liyu Chen , Rahul Jain , Haipeng Luo

The question whether the Simplex Algorithm admits an efficient pivot rule remains one of the most important open questions in discrete optimization. While many natural, deterministic pivot rules are known to yield exponential running times,…

Optimization and Control · Mathematics 2020-11-02 Yann Disser , Oliver Friedmann , Alexander V. Hopp

This paper explores the realm of infinite horizon average reward Constrained Markov Decision Processes (CMDPs). To the best of our knowledge, this work is the first to delve into the regret and constraint violation analysis of average…

Machine Learning · Computer Science 2024-10-31 Qinbo Bai , Washim Uddin Mondal , Vaneet Aggarwal

Whereas classical Markov decision processes maximize the expected reward, we consider minimizing the risk. We propose to evaluate the risk associated to a given policy over a long-enough time horizon with the help of a central limit…

Optimization and Control · Mathematics 2015-12-03 Pengqian Yu , Jia Yuan Yu , Huan Xu

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) are standard models for probabilistic systems with non-deterministic behaviours. Mean payoff (or long-run average reward) provides a mathematically elegant formalism to express performance related…

Performance · Computer Science 2017-09-08 Jan Křetínský , Tobias Meggendorfer

We introduce two-level discounted games played by two players on a perfect-information stochastic game graph. The upper level game is a discounted game and the lower level game is an undiscounted reachability game. Two-level games model…

Logic in Computer Science · Computer Science 2010-06-09 Krishnendu Chatterjee , Rupak Majumdar

It is well-known that for infinitely repeated games, there are computable strategies that have best responses, but no computable best responses. These results were originally proved for either specific games (e.g., Prisoner's dilemma), or…

Computer Science and Game Theory · Computer Science 2020-06-11 Jakub Dargaj , Jakob Grue Simonsen

The policy iteration method is a classical algorithm for solving optimal control problems. In this paper, we introduce a policy iteration method for Mean Field Games systems, and we study the convergence of this procedure to a solution of…

Analysis of PDEs · Mathematics 2021-07-12 Simone Cacace , Fabio Camilli , Alessandro Goffi

In this paper, we consider reinforcement learning of Markov Decision Processes (MDP) with peak constraints, where an agent chooses a policy to optimize an objective and at the same time satisfy additional constraints. The agent has to take…

Optimization and Control · Mathematics 2019-12-09 Ather Gattami

In this paper, we consider the gradual-impulse control problem of continuous-time Markov decision processes, where the system performance is measured by the expectation of the exponential utility of the total cost. We prove, under very…

Optimization and Control · Mathematics 2023-11-16 Xin Guo , Aiko Kurushima , Alexey Piunovskiy , Yi Zhang

In stochastic dynamic environments, team Markov games have emerged as a versatile paradigm for studying sequential decision-making problems of fully cooperative multi-agent systems. However, the optimality of the derived policies is usually…

Optimization and Control · Mathematics 2022-05-03 Feng Huang , Ming Cao , Long Wang

We study Markov potential games under the infinite horizon average reward criterion. Most previous studies have been for discounted rewards. We prove that both algorithms based on independent policy gradient and independent natural policy…

Machine Learning · Computer Science 2024-03-12 Min Cheng , Ruida Zhou , P. R. Kumar , Chao Tian

This note re-visits the rolling-horizon control approach to the problem of a Markov decision process (MDP) with infinite-horizon discounted expected reward criterion. Distinguished from the classical value-iteration approach, we develop an…

Optimization and Control · Mathematics 2022-06-07 Hyeong Soo Chang

Convergence of the policy iteration method for discrete and continuous optimal control problems holds under general assumptions. Moreover, in some circumstances, it is also possible to show a quadratic rate of convergence for the algorithm.…

Optimization and Control · Mathematics 2022-03-02 Fabio Camilli , Qing Tang

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…

Machine Learning · Computer Science 2020-07-16 Evrard Garcelon , Mohammad Ghavamzadeh , Alessandro Lazaric , Matteo Pirotta

We consider a risk-sensitive continuous-time Markov decision process over a finite time duration. Under the conditions that can be satisfied by unbounded transition and cost rates, we show the existence of an optimal policy, and the…

Optimization and Control · Mathematics 2018-11-29 Xin Guo , Qiuli Liu , Yi Zhang

We present an extension of two policy-iteration based algorithms on weighted graphs (viz., Markov Decision Problems and Max-Plus Algebras). This extension allows us to solve the following inverse problem: considering the weights of the…

Discrete Mathematics · Computer Science 2009-11-18 Laurent Fribourg , Etienne André