arXiv Machine Learning
Achieving an $O(1/N)$ Optimality Gap in Average-Reward Weakly-Coupled MDPs
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Statistics ML
Sep 2
Model Predictive Control is almost Optimal for Heterogeneous Restless Multi-armed Bandits
arXiv:2511.08097v2 Announce Type: replace-cross Abstract: We consider a general infinite horizon Heterogeneous Restless multi-armed Bandit (RMAB). Heterogeneity is a fundamental problem for many real...
arXiv Machine Learning
Jun 15
Lyapunov-Based Sample Complexity Analysis for Weakly-Coupled MDPs
arXiv:2606. 14095v1 Announce Type: new Abstract: We study the sample complexity of learning in average-reward weakly-coupled Markov decision processes (WCMDPs) and Restless Bandits (RBs) under a generative model.
arXiv Machine Learning
Jun 29
Learning in Markovian bandits with non-observable states and constrained decision epochs
arXiv:2606. 27448v1 Announce Type: new Abstract: This paper studies the problem of regret minimization in Markovian bandits with \emph{non-observable states} and possibly \emph{constrained} decision epochs.
arXiv Machine Learning
Jul 23
Asymptotically Optimal Regret for Reinforcement Learning without Horizon Dependence
arXiv:2607. 19854v1 Announce Type: new Abstract: We study horizon-free regret minimization for finite-horizon time-homogeneous tabular Markov decision processes with $S$ states, $A$ actions, horizon $H$, and per-trajectory total reward bounded by $1$.
arXiv Machine Learning
Jul 30
Top-$k$ Pareto Bandits: Hypervolume Regret for Multi-Objective Slate Selection
arXiv:2607. 26273v1 Announce Type: new Abstract: We consider a stochastic multi-objective bandit problem where, at each round, the agent selects a slate of $k$ arms and observes their $d$-dimensional reward vectors under semi-bandit feedback.
arXiv Machine Learning
1d ago
Nonpreemptive Scheduling While Learning Context-Dependent Service Rates
arXiv:2609.37660v1 Announce Type: new Abstract: We study nonpreemptive contextual queueing bandits in a single-server system. Each job is represented by a $d$-dimensional context vector; in each roun...