paper-with-me

Papers

Model Predictive Control is Almost Optimal for Restless Bandit

2024-10-08 · Nicolas Gast, Dheeraj Narasimha

We consider the discrete time infinite horizon average reward restless markovian bandit (RMAB) problem. We propose a \emph{model predictive control} based non-stationary policy with a rolling computational horizon $\tau$. At each time-slot, this policy solves a $\tau$ horizon linear program whose first control value is kept as a control for the RMAB. Our solution requires minimal assumptions and quantifies the loss in optimality in terms of $\tau$ and the number of arms, $N$. We show that its sub-optimality gap is $O(1/\sqrt{N})$ in general, and $\exp(-\Omega(N))$ under a local-stability condition. Our proof is based on a framework from dynamic control known as \emph{dissipativity}. Our solution easy to implement and performs very well in practice when compared to the state of the art. Further, both our solution and our proof methodology can easily be generalized to more general constrained MDP settings and should thus, be of great interest to the burgeoning RMAB community.

📄 PDF Abstract BibTeX arXiv:2410.06307

Code (0)

등록된 구현이 없습니다.

Tasks

Model Predictive Control

Similar Papers 제목 키워드 기반

Model Predictive Control is almost Optimal for Heterogeneous Restless Multi-armed Bandits

2025-11-11 · Dheeraj Narasimha, Nicolas Gast arxiv

We consider a general infinite horizon Heterogeneous Restless multi-armed Bandit (RMAB). Heterogeneity is a fundamental problem for many real-world systems largely because it resists many concentration arguments. In this…

Multi-Armed Bandits

Optimal Adaptive Learning in Uncontrolled Restless Bandit Problems

2011-07-20 · Cem Tekin, Mingyan Liu

In this paper we consider the problem of learning the optimal policy for uncontrolled restless bandit problems. In an uncontrolled restless bandit problem, there is a finite set of arms, each of which when pulled yields …

NeurWIN: Neural Whittle Index Network For Restless Bandits Via Deep RL

2021-10-05 · NeurIPS 2021 12 · Khaled Nakhleh, Santosh Ganji, Ping-Chun Hsieh, I-Hong Hou 외

Whittle index policy is a powerful tool to obtain asymptotically optimal solutions for the notoriously intractable problem of restless bandits. However, finding the Whittle indices remains a difficult problem for many pr…

Deep Reinforcement Learning

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

Achieving Exponential Asymptotic Optimality in Average-Reward Restless Bandits without Global Attractor Assumption

2024-05-28 · Yige Hong, Qiaomin Xie, Yudong Chen, Weina Wang

We consider the infinite-horizon average-reward restless bandit problem. We propose a novel \emph{two-set policy} that maintains two dynamic subsets of arms: one subset of arms has a nearly optimal state distribution and…