English
Related papers

Related papers: Strong Polynomiality of the Value Iteration Algori…

200 papers

We study existence and uniqueness of the fixed points solutions of a large class of non-linear variable discounted transfer operators associated to a sequential decision-making process. We establish regularity properties of these solutions,…

Dynamical Systems · Mathematics 2019-02-20 L. Cioletti , Elismar R. Oliveira

We study discrete-time discounted constrained Markov decision processes (CMDPs) on Borel spaces with unbounded reward functions. In our approach the transition probability functions are weakly or set-wise continuous. The reward functions…

Optimization and Control · Mathematics 2019-03-29 Eugene A. Feinberg , Anna Jaśkiewicz , Andrzej S. Nowak

Scientific explanation often requires inferring maximally predictive features from a given data set. Unfortunately, the collection of minimal maximally predictive features for most stochastic processes is uncountably infinite. In such…

Statistical Mechanics · Physics 2017-05-31 Sarah E. Marzen , James P. Crutchfield

We consider the expressivity of Markov rewards in sequential decision making under uncertainty. We view reward functions in Markov Decision Processes (MDPs) as a means to characterize desired behaviors of agents. Assuming desired behaviors…

Artificial Intelligence · Computer Science 2023-07-25 Shuwa Miura

This paper studies convergence properties of optimal values and actions for discounted and average-cost Markov Decision Processes (MDPs) with weakly continuous transition probabilities and applies these properties to the stochastic…

Optimization and Control · Mathematics 2017-03-21 Eugene A. Feinberg , Mark E. Lewis

We provide performance guarantees for a variant of simulation-based policy iteration for controlling Markov decision processes that involves the use of stochastic approximation algorithms along with state-of-the-art techniques that are…

Machine Learning · Computer Science 2022-10-17 Anna Winnicki , R. Srikant

The policy improvement bound on the difference of the discounted returns plays a crucial role in the theoretical justification of the trust-region policy optimization (TRPO) algorithm. The existing bound leads to a degenerate bound when the…

Machine Learning · Computer Science 2021-07-20 J. G. Dai , Mark Gluzman

This paper discusses algorithms for solving Markov decision processes (MDPs) that have monotone optimal policies. We propose a two-stage alternating convex optimization scheme that can accelerate the search for an optimal policy by…

Systems and Control · Computer Science 2017-04-04 Robert Mattila , Cristian R. Rojas , Vikram Krishnamurthy , Bo Wahlberg

Processes (MDPs) often require frequent decision making, that is, taking an action every microsecond, second, or minute. Infinite horizon discount reward formulation is still relevant for a large portion of these applications, because…

Optimization and Control · Mathematics 2014-12-17 Yin-Lam Chow , Junjie Qin

Solving partially observable Markov decision processes (POMDPs) is highly intractable in general, at least in part because the optimal policy may be infinitely large. In this paper, we explore the problem of finding the optimal policy from…

Artificial Intelligence · Computer Science 2013-01-30 Nicolas Meuleau , Kee-Eung Kim , Leslie Pack Kaelbling , Anthony R. Cassandra

We consider the problem of computing the value and an optimal strategy for minimizing the expected termination time in one-counter Markov decision processes. Since the value may be irrational and an optimal strategy may be rather…

Formal Languages and Automata Theory · Computer Science 2012-05-08 Tomáš Brázdil , Antonín Kučera , Petr Novotný , Dominik Wojtczak

Policy gradient methods are among the most effective methods in challenging reinforcement learning problems with large state and/or action spaces. However, little is known about even their most basic theoretical convergence properties,…

Machine Learning · Computer Science 2020-10-16 Alekh Agarwal , Sham M. Kakade , Jason D. Lee , Gaurav Mahajan

We consider the problem of controlling a fully specified Markov decision process (MDP), also known as the planning problem, when the state space is very large and calculating the optimal policy is intractable. Instead, we pursue the more…

Optimization and Control · Mathematics 2019-01-09 Yasin Abbasi-Yadkori , Peter L. Bartlett , Xi Chen , Alan Malek

This paper establishes that an MDP with a unique optimal policy and ergodic associated transition matrix ensures the convergence of various versions of the Value Iteration algorithm at a geometric rate that exceeds the discount factor…

Machine Learning · Computer Science 2024-06-17 Arsenii Mustafin , Alex Olshevsky , Ioannis Ch. Paschalidis

We tackle the issue of finding a good policy when the number of policy updates is limited. This is done by approximating the expected policy reward as a sequence of concave lower bounds which can be efficiently maximized, drastically…

Artificial Intelligence · Computer Science 2016-12-30 Nicolas Le Roux

This paper presents sufficient conditions for the existence of stationary optimal policies for average-cost Markov Decision Processes with Borel state and action sets and with weakly continuous transition probabilities. The one-step cost…

Optimization and Control · Mathematics 2012-02-21 Eugene A. Feinberg , Pavlo O. Kasyanov , Nina V. Zadoianchuk

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…

Artificial Intelligence · Computer Science 2025-06-17 Ali Asadi , Krishnendu Chatterjee , Jakob de Raaij

Finding optimal policies which maximize long term rewards of Markov Decision Processes requires the use of dynamic programming and backward induction to solve the Bellman optimality equation. However, many real-world problems require…

Machine Learning · Computer Science 2023-01-10 Mridul Agarwal , Vaneet Aggarwal

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.…

Artificial Intelligence · Computer Science 2025-05-05 Dibyangshu Mukherjee , Shivaram Kalyanakrishnan

What are the functionals of the reward that can be computed and optimized exactly in Markov Decision Processes?In the finite-horizon, undiscounted setting, Dynamic Programming (DP) can only handle these operations efficiently for certain…

Artificial Intelligence · Computer Science 2024-02-20 Alexandre Marthe , Aurélien Garivier , Claire Vernade
‹ Prev 1 3 4 5 6 7 10 Next ›