paper-with-me

홈 › Papers

Multi-Armed Bandits for Correlated Markovian Environments with Smoothed Reward Feedback

2018-03-11 · Tanner Fiez, Shreyas Sekar, Lillian J. Ratliff

We study a multi-armed bandit problem in a dynamic environment where arm rewards evolve in a correlated fashion according to a Markov chain. Different than much of the work on related problems, in our formulation a learning algorithm does not have access to either a priori information or observations of the state of the Markov chain and only observes smoothed reward feedback following time intervals we refer to as epochs. We demonstrate that existing methods such as UCB and $\varepsilon$-greedy can suffer linear regret in such an environment. Employing mixing-time bounds on Markov chains, we develop algorithms called EpochUCB and EpochGreedy that draw inspiration from the aforementioned methods, yet which admit sublinear regret guarantees for the problem formulation. Our proposed algorithms proceed in epochs in which an arm is played repeatedly for a number of iterations that grows linearly as a function of the number of times an arm has been played in the past. We analyze these algorithms under two types of smoothed reward feedback at the end of each epoch: a reward that is the discount-average of the discounted rewards within an epoch, and a reward that is the time-average of the rewards within an epoch.

📄 PDF Abstract BibTeX arXiv:1803.04008

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Armed BanditsQ-Learning

Similar Papers 제목 키워드 기반

MARBLE: Multi-Armed Restless Bandits in Latent Markovian Environment

2025-11-12 · Mohsen Amiri, Konstantin Avrachenkov, Ibtihal El Mimouni, Sindri Magnússon arxiv

Restless Multi-Armed Bandits (RMABs) are powerful models for decision-making under uncertainty, yet classical formulations typically assume fixed dynamics, an assumption often violated in nonstationary environments. We i…

Multi-Armed Bandits

Flickering Multi-Armed Bandits

2026-02-19 · Sourav Chakraborty, Amit Kiran Rege, Claire Monteleoni, Lijun Chen arxiv

We introduce Flickering Multi-Armed Bandits (FMAB) to model sequential decision-making in environments with changing action availability, where accessibility of the next action is restricted to a subset dependent on the …

Multi-Armed Bandits

A Hoeffding Inequality for Finite State Markov Chains and its Applications to Markovian Bandits

2020-01-05 · Vrettos Moulos

This paper develops a Hoeffding inequality for the partial sums $\sum_{k=1}^n f (X_k)$, where $\{X_k\}_{k \in \mathbb{Z}_{> 0}}$ is an irreducible Markov chain on a finite state space $S$, and $f : S \to [a, b]$ is a rea…

Fairness of Exposure in Online Restless Multi-armed Bandits

2024-02-09 · Archit Sood, Shweta Jain, Sujit Gujar

Restless multi-armed bandits (RMABs) generalize the multi-armed bandits where each arm exhibits Markovian behavior and transitions according to their transition dynamics. Solutions to RMAB exist for both offline and onli…

FairnessMulti-Armed Bandits

Asymptotic Randomised Control with applications to bandits

2020-10-14 · Samuel N. Cohen, Tanut Treetanthiploet

We consider a general multi-armed bandit problem with correlated (and simple contextual and restless) elements, as a relaxed control problem. By introducing an entropy regularisation, we obtain a smooth asymptotic approx…

ARCMulti-Armed Bandits