arXiv:2607. 02196v1 Announce Type: new Abstract: We study online resource allocation when both rewards and consumption sizes may be continuously distributed.
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...
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: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:2609.36945v1 Announce Type: new Abstract: We study the learning dynamics of fine-tuning a policy model on self-generated and reward-weighted data, with particular focus on a generalized version...
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:2608. 07922v1 Announce Type: new Abstract: Adaptive learning needs both a state that preserves what observations imply and opportunities to act on that state.
The paper investigates online fair allocation of sequential items to agents with heterogeneous preferences, aiming to maximize generalized-mean welfare. In an i.i.d. arrival setting, a pure greedy algorithm achieves near-optimal “~O(1/T)” average regret without needing distributional knowledge. For nonstationary arrivals, the authors show that a single historical sample per distribution suffices to recover the same regret rate, using re-solving algorithms that remain robust to distribution shifts.
arXiv:2607. 27626v1 Announce Type: new Abstract: Safety-critical IoT systems such as industrial closed-loop control, V2X coordination, and remote teleoperation require every sensor's peak Age of Information (peak AoI, also abbreviated PAoI) to stay below a hard per-slot deadline, not merely an average bound.
The paper introduces a computationally efficient algorithm for infinite-horizon average-reward constrained Markov decision processes (CMDPs) under weak communication. It achieves a high-probability regret and cumulative constraint violation of ×O(√T) in the tabular setting, matching optimal dependence up to logarithmic factors. The method augments the state with cumulative constraint violation, reshapes rewards using a Huber potential, and applies finite-horizon approximation with optimistic value iteration to maintain bounded per-step rewards.
arXiv:2409. 14557v4 Announce Type: replace-cross Abstract: We study a structured class of Markov Decision Processes, known as Exo-MDPs, in which the state space is partitioned into exogenous and endogenous components.
arXiv:2609. 30556v1 Announce Type: new Abstract: We study dynamic regret in online convex optimization with an \emph{indicator switching cost}: a fixed penalty incurred whenever two consecutive decisions differ.