Research map / Bandits and online learning / Multi-armed bandits
Tightening Regret Lower and Upper Bounds in Restless Rising Bandits
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Theoretical study of restless rising bandits (rising and rising concave arm-reward settings), tightening regret lower and upper bounds.
Problem
Regret minimization in restless multi-armed bandits whose expected rewards evolve over time, specifically the rising and rising concave structured subclasses.
Approach
Derives tighter regret lower and upper bounds for restless rising and rising concave bandits than previously known, using the structure where each arm's expected reward is non-decreasing (and concave in the rising concave case) over time.
Experimental setup
Metrics: regret
Closest papers by meaning
- Bayesian Regret Minimization in Offline Bandits (ICML 2024 · similarity 0.89)
- DOPL: Direct Online Preference Learning for Restless Bandits with Preference Feedback (ICLR 2025 · similarity 0.89)
- Provably Efficient Reinforcement Learning for Adversarial Restless Multi-Armed Bandits with Unknown Transitions and Bandit Feedback (ICML 2024 · similarity 0.89)
- Nash Social Welfare for Multi Armed Bandits: Trajectory-wise Expected and High Probability Regret (NeurIPS 2026 · similarity 0.89)
- Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown Marginals (ICML 2024 · similarity 0.89)
- Adaptive Regret for Bandits Made Possible: Two Queries Suffice (ICLR 2024 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.