Research map / Bandits and online learning / Online convex optimization and games
Decentralized Learning in Online Queuing Systems
Flore Sentenac, Etienne Boursier, Vianney Perchet
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use cooperative decentralized learning with synchronized exploration and shared randomness | ADeQuA · Queuing systems with slack η>1 | strong stability: η>1; η>2 | Improved |
| Use ADeQuA instead of EXP3.P.1 | Toy instance with η<2 · Toy queuing instance, η<2 | queue stability | Improved |
| Use ADeQuA instead of individual no-regret strategies | Toy instance with η>2 · Toy queuing instance, η>2 | learning speed | Hurt |
| Use exploration probability proportional to t^(-1/4) rather than t^(-1/5) (ablation) | ADeQuA · Toy simulations | exploration speed: t^{-1/4}; t^{-1/5} | Improved |
| Replace regularized dominant mapping with a mapping without the regularizing term (ablation) | ADeQuA · Queuing systems with equal or close arrival/service parameters | stability | Hurt |
Closest papers by meaning
- Impact of Decentralized Learning on Player Utilities in Stackelberg Games (ICML 2024 · similarity 0.88)
- Decentralized Scheduling with QoS Constraints: Achieving O(1) QoS Regret of Multi-Player Bandits (AAAI 2024 · similarity 0.87)
- Near-Optimal Regret-Queue Length Tradeoff in Online Learning for Two-Sided Markets (NeurIPS 2025 · similarity 0.86)
- Decentralized Noncooperative Games with Coupled Decision-Dependent Distributions (NeurIPS 2024 · similarity 0.85)
- Mediator Interpretation and Faster Learning Algorithms for Linear Correlated Equilibria in General Sequential Games (ICLR 2024 · similarity 0.85)
- Convergence of No-Swap-Regret Dynamics in Self-Play (NeurIPS 2024 · similarity 0.85)
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.
