English
Related papers

Related papers: Optimistic Policy Iteration for MDPs with Acyclic …

200 papers

Standard Markov decision process (MDP) and reinforcement learning algorithms optimize the policy with respect to the expected gain. We propose an algorithm which enables to optimize an alternative objective: the probability that the gain is…

Machine Learning · Computer Science 2023-03-06 Vincent Corlay , Jean-Christophe Sibel

We present the first finite time global convergence analysis of policy gradient in the context of infinite horizon average reward Markov decision processes (MDPs). Specifically, we focus on ergodic tabular MDPs with finite state and action…

Machine Learning · Computer Science 2024-03-12 Navdeep Kumar , Yashaswini Murthy , Itai Shufaro , Kfir Y. Levy , R. Srikant , Shie Mannor

In this paper, we study the Markovian Pandora's Box Problem, where decisions are governed by both order constraints and Markovianly correlated rewards, structured within a shared directed acyclic graph. To the best of our knowledge,…

Computer Science and Game Theory · Computer Science 2025-02-04 Yuanyuan Yang , Ruimin Zhang , Jamie Morgenstern , Haifeng Xu

A new class of stochastic processes called independent and periodically identically distributed (i.p.i.d.) processes is defined to capture periodically varying statistical behavior. A novel Bayesian theory is developed for detecting a…

Signal Processing · Electrical Eng. & Systems 2019-04-09 Taposh Banerjee , Prudhvi Gurram , Gene Whipps

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

We introduce Markov Neural Processes (MNPs), a new class of Stochastic Processes (SPs) which are constructed by stacking sequences of neural parameterised Markov transition operators in function space. We prove that these Markov transition…

Machine Learning · Statistics 2023-05-26 Jin Xu , Emilien Dupont , Kaspar Märtens , Tom Rainforth , Yee Whye Teh

Online learning algorithms are designed to perform in non-stationary environments, but generally there is no notion of a dynamic state to model constraints on current and future actions as a function of past actions. State-based models are…

Machine Learning · Computer Science 2015-09-01 Peng Guan , Maxim Raginsky , Rebecca Willett

We show that combinations of optimal (stationary) policies in unichain Markov decision processes are optimal. That is, let M be a unichain Markov decision process with state space S, action space A and policies \pi_j^*: S -> A (1\leq j\leq…

Combinatorics · Mathematics 2007-05-23 Ronald Ortner

We consider a Markov decision process with deterministic state transition dynamics, adversarially generated rewards that change arbitrarily from round to round, and a bandit feedback model in which the decision maker only observes the…

Computer Science and Game Theory · Computer Science 2012-10-19 Raman Arora , Ofer Dekel , Ambuj Tewari

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

We consider lexicographic bi-objective problems on Markov Decision Processes (MDPs), where we optimize one objective while guaranteeing optimality of another. We propose a two-stage technique for solving such problems when the objectives…

Computer Science and Game Theory · Computer Science 2023-08-17 Damien Busatto-Gaston , Debraj Chakraborty , Anirban Majumdar , Sayan Mukherjee , Guillermo A. Pérez , Jean-François Raskin

We study the relation between different Markov Decision Process (MDP) frameworks in the machine learning and econometrics literatures, including the standard MDP, the entropy and general regularized MDP, and stochastic MDP, where the latter…

Optimization and Control · Mathematics 2020-08-19 Tien Mai , Patrick Jaillet

Several hierarchical reinforcement learning methods leverage planning to create a graph or sequences of intermediate goals, guiding a lower-level goal-conditioned (GC) policy to reach some final goals. The low-level policy is typically…

Machine Learning · Computer Science 2025-03-31 Olivier Serris , Stéphane Doncieux , Olivier Sigaud

Because failures in distribution systems caused by extreme weather events directly result in consumers' outages, this paper proposes a state-based decision-making model with the objective of mitigating loss of load to improve the…

Optimization and Control · Mathematics 2019-04-02 Chong Wang , Ping Ju , Shunbo Lei , Zhaoyu Wang , Yunhe Hou

We study the optimal transport problem for pairs of stationary finite-state Markov chains, with an emphasis on the computation of optimal transition couplings. Transition couplings are a constrained family of transport plans that capture…

Optimization and Control · Mathematics 2021-09-20 Kevin O'Connor , Kevin McGoff , Andrew B. Nobel

Policy gradient methods are extensively used in reinforcement learning as a way to optimize expected return. In this paper, we explore the evolution of the policy parameters, for a special class of exactly solvable POMDPs, as a…

Machine Learning · Computer Science 2020-11-04 Gavin McCracken , Colin Daniels , Rosie Zhao , Anna Brandenberger , Prakash Panangaden , Doina Precup

Recursive stochastic algorithms have gained significant attention in the recent past due to data driven applications. Examples include stochastic gradient descent for solving large-scale optimization problems and empirical dynamic…

Machine Learning · Computer Science 2020-07-27 Abhishek Gupta , Hao Chen , Jianzong Pi , Gaurav Tendolkar

Robust Markov Decision Processes (MDPs) are a powerful framework for modeling sequential decision-making problems with model uncertainty. This paper proposes the first first-order framework for solving robust MDPs. Our algorithm interleaves…

Optimization and Control · Mathematics 2021-01-18 Julien Grand-Clément , Christian Kroer

This paper discusses the functional stability of closed-loop Markov Chains under optimal policies resulting from a discounted optimality criterion, forming Markov Decision Processes (MDPs). We investigate the stability of MDPs in the sense…

Systems and Control · Electrical Eng. & Systems 2022-04-01 Arash Bahari Kordabad , Sebastien Gros

We consider partially observable Markov decision processes (POMDPs) with a set of target states and positive integer costs associated with every transition. The traditional optimization objective (stochastic shortest path) asks to minimize…

Artificial Intelligence · Computer Science 2016-05-12 Tomáš Brázdil , Krishnendu Chatterjee , Martin Chmelík , Anchit Gupta , Petr Novotný