English
Related papers

Related papers: Asymptotically Optimal Policies for Weakly Coupled…

200 papers

We consider a dynamic programming (DP) approach to approximately solving an infinite-horizon constrained Markov decision process (CMDP) problem with a fixed initial-state for the expected total discounted-reward criterion with a…

Optimization and Control · Mathematics 2023-08-08 Hyeong Soo Chang

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

This work studies discrete-time discounted Markov decision processes with continuous state and action spaces and addresses the inverse problem of inferring a cost function from observed optimal behavior. We first consider the case in which…

Optimization and Control · Mathematics 2024-05-27 Angeliki Kamoutsi , Peter Schmitt-Förster , Tobias Sutter , Volkan Cevher , John Lygeros

Algorithms for the Multi-Armed Bandit (MAB) problem play a central role in sequential decision-making and have been extensively explored both theoretically and numerically. While most classical approaches aim to identify the arm with the…

Machine Learning · Computer Science 2026-04-02 Gabriel Turinici

We consider minimisation of dynamic regret in non-stationary bandits with a slowly varying property. Namely, we assume that arms' rewards are stochastic and independent over time, but that the absolute difference between the expected…

Machine Learning · Computer Science 2021-10-26 Ramakrishnan Krishnamurthy , Aditya Gopalan

We study the limit behaviour of upper and lower bounds on expected time averages in imprecise Markov chains; a generalised type of Markov chain where the local dynamics, traditionally characterised by transition probabilities, are now…

Probability · Mathematics 2021-02-10 Natan T'Joens , Jasper De Bock

The Whittle index, which characterizes optimal policies for controlling certain single restless bandit projects (a Markov decision process with two actions: active and passive) is the basis for a widely used heuristic index policy for the…

Optimization and Control · Mathematics 2021-05-06 José Niño-Mora

The purpose of this paper is to provide further understanding into the structure of the sequential allocation ("stochastic multi-armed bandit", or MAB) problem by establishing probability one finite horizon bounds and convergence rates for…

Machine Learning · Statistics 2015-12-18 Wesley Cowan , Michael N. Katehakis

The problem of rested and restless multi-armed bandits with constrained availability of arms is considered. The states of arms evolve in Markovian manner and the exact states are hidden from the decision maker. First, some structural…

Systems and Control · Computer Science 2017-10-20 Varun Mehta , Rahul Meshram , Kesav Kaza , S. N. Merchant

This paper presents a new condition for the existence of optimal stationary policies in average-cost continuous-time Markov decision processes with unbounded cost and transition rates, arising from controlled queueing systems. This…

Optimization and Control · Mathematics 2015-04-23 Cao Ping , Xie Jingui

We consider a policy gradient algorithm applied to a finite-arm bandit problem with Bernoulli rewards. We allow learning rates to depend on the current state of the algorithm, rather than use a deterministic time-decreasing learning rate.…

Machine Learning · Computer Science 2021-09-24 Denis Denisov , Neil Walton

The multi-armed bandit(MAB) is a classical sequential decision problem. Most work requires assumptions about the reward distribution (e.g., bounded), while practitioners may have difficulty obtaining information about these distributions to…

Machine Learning · Computer Science 2023-12-14 Han Qi , Fei Guo , Li Zhu

This paper puts forward the concept that learning to take safe actions in unknown environments, even with probability one guarantees, can be achieved without the need for an unbounded number of exploratory trials. This is indeed possible,…

Systems and Control · Electrical Eng. & Systems 2023-02-14 Agustin Castellano , Hancheng Min , Juan Bazerque , Enrique Mallada

Controlled discrete time Markov processes are studied first with long run general discounting functional. It is shown that optimal strategies for average reward per unit time problem are also optimal for average generally discounting…

Optimization and Control · Mathematics 2023-06-27 Łukasz Stettner

In this paper, we focus on formal synthesis of control policies for finite Markov decision processes with non-negative real-valued costs. We develop an algorithm to automatically generate a policy that guarantees the satisfaction of a…

Logic in Computer Science · Computer Science 2013-09-10 Maria Svorenova , Ivana Cerna , Calin Belta

We consider a singular control problem that aims to maximize the expected cumulative rewards, where the instantaneous returns depend on the state of a controlled process. The contributions of this paper are twofold. Firstly, to establish…

Optimization and Control · Mathematics 2025-06-23 Mauricio Junca , Harold Moreno-Franco , Jose Luis Perez

Recent work has considered natural variations of the multi-armed bandit problem, where the reward distribution of each arm is a special function of the time passed since its last pulling. In this direction, a simple (yet widely applicable)…

Machine Learning · Computer Science 2021-05-25 Alexia Atsidakou , Orestis Papadigenopoulos , Soumya Basu , Constantine Caramanis , Sanjay Shakkottai

A standard assumption in Reinforcement Learning is that the agent observes every visited state-action pair in the associated Markov Decision Process (MDP), along with the per-step rewards. Strong theoretical results are known in this…

Machine Learning · Computer Science 2026-02-03 Zhengjia Zhuo , Anupam Gupta , Viswanath Nagarajan

Motivated by the fact that humans like some level of unpredictability or novelty, and might therefore get quickly bored when interacting with a stationary policy, we introduce a novel non-stationary bandit problem, where the expected reward…

Machine Learning · Computer Science 2022-03-08 Pierre Laforgue , Giulia Clerici , Nicolò Cesa-Bianchi , Ran Gilad-Bachrach

We consider the channel access problem under imperfect sensing of channel state in a multi-channel opportunistic communication system, where the state of each channel evolves as an independent and identically distributed Markov process. The…

Networking and Internet Architecture · Computer Science 2012-02-03 Kehao Wang , Lin Chen , Quan Liu , Khaldoun Al Agha