English
Related papers

Related papers: Optimistic Policy Iteration for MDPs with Acyclic …

200 papers

Interval Markov decision processes (IMDPs) generalise classical MDPs by having interval-valued transition probabilities. They provide a powerful modelling tool for probabilistic systems with an additional variation or uncertainty that…

Systems and Control · Computer Science 2017-07-07 Ernst Moritz Hahn , Vahid Hashemi , Holger Hermanns , Morteza Lahijanian , Andrea Turrini

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

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

Long-run average optimization problems for Markov decision processes (MDPs) require constructing policies with optimal steady-state behavior, i.e., optimal limit frequency of visits to the states. However, such policies may suffer from…

Multiagent Systems · Computer Science 2023-12-20 David Klaška , Antonín Kučera , Vojtěch Kůr , Vít Musil , Vojtěch Řehák

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…

Machine Learning · Computer Science 2019-12-02 Sarthak Consul , Bhishma Dedhia , Kumar Ashutosh , Parthasarathi Khirwadkar

Partially observable Markov decision processes (POMDPs) are standard models for dynamic systems with probabilistic and nondeterministic behaviour in uncertain environments. We prove that in POMDPs with long-run average objective, the…

Computer Science and Game Theory · Computer Science 2022-09-29 Krishnendu Chatterjee , Raimundo Saona , Bruno Ziliotto

Regularization of control policies using entropy can be instrumental in adjusting predictability of real-world systems. Applications benefiting from such approaches range from, e.g., cybersecurity, which aims at maximal unpredictability, to…

Systems and Control · Electrical Eng. & Systems 2026-02-18 Menno van Zutphen , Giannis Delimpaltadakis , Maurice Heemels , Duarte Antunes

Recently discovered polyhedral structures of the value function for finite state-action discounted Markov decision processes (MDP) shed light on understanding the success of reinforcement learning. We investigate the value function polytope…

Machine Learning · Computer Science 2022-06-27 Yue Wu , Jesús A. De Loera

We introduce synchronizing objectives for Markov decision processes (MDP). Intuitively, a synchronizing objective requires that eventually, at every step there is a state which concentrates almost all the probability mass. In particular, it…

Logic in Computer Science · Computer Science 2011-02-22 Laurent Doyen , Thierry Massart , Mahsa Shirmohammadi

In this paper we investigate several geometric properties of the set of occupancy measures. In particular, we analyse the structure of the faces generated by a given occupancy measure, together with their relative algebraic interior. We…

Optimization and Control · Mathematics 2025-12-22 Francois Dufour , Tomas Prieto-Rumeau

This paper proposes an agent-based optimistic policy iteration (OPI) scheme for learning stationary optimal stochastic policies in multi-agent Markov Decision Processes (MDPs), in which agents incur a Kullback-Leibler (KL) divergence cost…

Artificial Intelligence · Computer Science 2024-10-22 Khaled Nakhleh , Ceyhun Eksin , Sabit Ekin

We propose a new method for optimistic planning in infinite-horizon discounted Markov decision processes based on the idea of adding regularization to the updates of an otherwise standard approximate value iteration procedure. This…

Machine Learning · Computer Science 2023-06-16 Antoine Moulin , Gergely Neu

Solving Markov Decision Processes (MDPs) remains a central challenge in sequential decision-making, especially when dealing with large state spaces and long-term optimization criteria. A key step in Bellman dynamic programming algorithms is…

Optimization and Control · Mathematics 2025-08-04 Youssef Ait El Mahjoub , Jean-Michel Fourneau , Salma Alouah

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

A classical approach to formal policy synthesis in stochastic dynamical systems is to construct a finite-state abstraction, often represented as a Markov decision process (MDP). The correctness of these approaches hinges on a behavioural…

Systems and Control · Electrical Eng. & Systems 2025-08-08 Thom Badings , Alessandro Abate

In this work, we study dynamic programming (DP) algorithms for partially observable Markov decision processes with jointly continuous and discrete state-spaces. We consider a class of stochastic systems which have coupled discrete and…

Optimization and Control · Mathematics 2019-03-07 Donghwan Lee , Niao He , Jianghai Hu

We revisit the finite time analysis of policy gradient methods in the one of the simplest settings: finite state and action MDPs with a policy class consisting of all stochastic policies and with exact gradient evaluations. There has been…

Machine Learning · Computer Science 2021-12-14 Jalaj Bhandari , Daniel Russo

We consider an exhaustive polling system with three nodes in its transient regime under a switching rule of generalized greedy type. We show that, for the system with Poisson arrivals and service times with finite second moment, the…

Probability · Mathematics 2007-05-23 I. M. MacPhee , M. V. Menshikov , S. Popov , S. Volkov

Graph games and Markov decision processes (MDPs) are standard models in reactive synthesis and verification of probabilistic systems with nondeterminism. The class of $\omega$-regular winning conditions; e.g., safety, reachability,…

Logic in Computer Science · Computer Science 2019-06-28 Pranav Ashok , Tomáš Brázdil , Krishnendu Chatterjee , Jan Křetínský , Christoph H. Lampert , Viktor Toman

Typical Recommender systems adopt a static view of the recommendation process and treat it as a prediction problem. We argue that it is more appropriate to view the problem of generating recommendations as a sequential decision problem and,…

Machine Learning · Computer Science 2015-05-19 Guy Shani , Ronen I. Brafman , David Heckerman