Adapting to Decision-Relevant Non-Stationarity in Decentralized Heterogeneous Bandits
cs.LG
Submitted: 2026-09-15
Updated: 2026-09-15
Comments: 90 pages, 18 figures
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Finite-Time Guarantees for Multi-Agent Combinatorial Bandits with Nonstationary Rewards
- Distributed Consensus Algorithm for Decision-Making in Multi-agent Multi-armed Bandit
- On Upper-Confidence Bound Policies for Non-Stationary Bandit Problems
- Catoni-Style Change Point Detection for Regret Minimization in Non-Stationary Heavy-Tailed Bandits
- Time-uniform, nonparametric, nonasymptotic confidence sequences
- Robust Decentralized Multi-armed Bandits: From Corruption-Resilience to Byzantine-Resilience
- Dynamic Regret for Non-Stationary Linear Bandits via Misspecification Reductions
- Constrained Feedback Learning for Non-Stationary Multi-Armed Bandits
- Distributed Multi-Agent Bandits Over Erd\H{o}s-R'enyi Random Networks
- A Definition of Non-Stationary Bandits
- Heterogeneous Multi-Agent Bandits with Parsimonious Hints
- Adaptive Smooth Non-Stationary Bandits
- Multi-Objective Multi-Agent Bandits: From Learning Efficiency to Fairness Optimization
- Multi-agent Multi-armed Bandit with Fully Heavy-tailed Dynamics
- Distributed Bandit Learning: Near-Optimal Regret with Efficient Communication
- Estimating means of bounded random variables by betting
- Heterogeneous Multi-agent Multi-armed Bandits on Stochastic Block Models
- Distributed Bandits with Heterogeneous Agents
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks