3 papers
cs.LG2026
Restless Bandits with Individual Penalty Constraints: Near-Optimal Indices and Deep Reinforcement Learning
Nida Zamir, I-Hong Hou
This paper investigates the Restless Multi-Armed Bandit (RMAB) framework under individual penalty constraints to address resource allocation challenges in dynamic wireless networke…
cs.LG2024
Deep Index Policy for Multi-Resource Restless Matching Bandit and Its Application in Multi-Channel Scheduling
Nida Zamir, I-Hong Hou
Scheduling in multi-channel wireless communication system presents formidable challenges in effectively allocating resources. To address these challenges, we investigate a multi-re…
cs.LG2024
Distributed No-Regret Learning for Multi-Stage Systems with End-to-End Bandit Feedback
I-Hong Hou
This paper studies multi-stage systems with end-to-end bandit feedback. In such systems, each job needs to go through multiple stages, each managed by a different agent, before gen…