English
Related papers

Related papers: Yet Another Distributional Bellman Equation

200 papers

This paper is devoted to studying constrained continuous-time Markov decision processes (MDPs) in the class of randomized policies depending on state histories. The transition rates may be unbounded, the reward and costs are admitted to be…

Probability · Mathematics 2012-01-04 Xianping Guo , Xinyuan Song

The planning domain has experienced increased interest in the formal synthesis of decision-making policies. This formal synthesis typically entails finding a policy which satisfies formal specifications in the form of some well-defined…

Artificial Intelligence · Computer Science 2021-11-30 George K. Atia , Andre Beckus , Ismail Alkhouri , Alvaro Velasquez

Previous work has separately addressed different forms of action, state and action-state entropy regularization, pure exploration and space occupation. These problems have become extremely relevant for regularization, generalization,…

Machine Learning · Computer Science 2023-02-03 Dmytro Grytskyy , Jorge Ramírez-Ruiz , Rubén Moreno-Bote

Multi-agent planning under stochastic dynamics is usually formalised using decentralized (partially observable) Markov decision processes ( MDPs) and reachability or expected reward specifications. In this paper, we propose a different…

Logic in Computer Science · Computer Science 2025-02-20 Francesco Pontiggia , Filip Macák , Roman Andriushchenko , Michele Chiari , Milan Češka

We study countably infinite Markov decision processes (MDPs) with real-valued transition rewards. Every infinite run induces the following sequences of payoffs: 1. Point payoff (the sequence of directly seen transition rewards), 2. Mean…

Computational Complexity · Computer Science 2023-06-22 Richard Mayr , Eric Munday

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

This paper investigates MDPs with intermittent state information. We consider a scenario where the controller perceives the state information of the process via an unreliable communication channel. The transmissions of state information…

Artificial Intelligence · Computer Science 2025-02-17 Gongpu Chen , Soung-Chang Liew

Markov Decision Processes (MDPs) are a popular class of models suitable for solving control decision problems in probabilistic reactive systems. We consider parametric MDPs (pMDPs) that include parameters in some of the transition…

Logic in Computer Science · Computer Science 2018-06-14 Sebastian Arming , Ezio Bartocci , Krishnendu Chatterjee , Joost-Pieter Katoen , Ana Sokolova

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

We seek to learn an effective policy for a Markov Decision Process (MDP) with continuous states via Q-Learning. Given a set of basis functions over state action pairs we search for a corresponding set of linear weights that minimizes the…

Machine Learning · Computer Science 2013-09-27 Charles Tripp , Ross D. Shachter

We study an optimal stopping problem under non-exponential discounting, where the state process is a multi-dimensional continuous strong Markov process. The discount function is taken to be log sub-additive, capturing decreasing impatience…

Mathematical Finance · Quantitative Finance 2021-07-14 Yu-Jui Huang , Zhenhua Wang

We study a class of infinite-horizon average-cost Markov Decision Processes (MDPs) whose reward and transition structures are nearly separable. For the totally separable baseline (that is, with no perturbation), we derive an explicit…

Optimization and Control · Mathematics 2025-10-28 Dhairya Kantawala

We investigate discrete-time mean-variance portfolio selection problems viewed as a Markov decision process. We transform the problems into a new model with deterministic transition function for which the Bellman optimality equation holds.…

Optimization and Control · Mathematics 2025-09-23 Nicole Bäuerle , Anna Jaśkiewicz

Many problems in sequential decision making and stochastic control often have natural multiscale structure: sub-tasks are assembled together to accomplish complex goals. Systematically inferring and leveraging hierarchical structure,…

Artificial Intelligence · Computer Science 2012-12-06 Jake Bouvrie , Mauro Maggioni

The Markov assumption in Markov Decision Processes (MDPs) is fundamental in reinforcement learning, influencing both theoretical research and practical applications. Existing methods that rely on the Bellman equation benefit tremendously…

Methodology · Statistics 2024-09-24 Chuyun Ye , Lixing Zhu , Ruoqing Zhu

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

Contextual Markov decision processes (CMDPs) describe a class of reinforcement learning problems in which the transition kernels and reward functions can change over time with different MDPs indexed by a context variable. While CMDPs serve…

Machine Learning · Computer Science 2024-02-06 Junze Deng , Yuan Cheng , Shaofeng Zou , Yingbin Liang

For a Markov decision process with countably infinite states, the optimal value may not be achievable in the set of stationary policies. In this paper, we study the existence conditions of an optimal stationary policy in a countable-state…

Optimization and Control · Mathematics 2020-07-06 Li Xia , Xianping Guo , Xi-Ren Cao

We consider the problem of computing optimal policies in average-reward Markov decision processes. This classical problem can be formulated as a linear program directly amenable to saddle-point optimization methods, albeit with a number of…

Optimization and Control · Mathematics 2020-01-13 Joan Bas-Serrano , Gergely Neu

We derive distributional limits for empirical transport distances between probability measures supported on countable sets. Our approach is based on sensitivity analysis of optimal values of infinite dimensional mathematical programs and a…

Probability · Mathematics 2018-09-18 Carla Tameling , Max Sommerfeld , Axel Munk