Research map / Bandits and online learning / Multi-armed bandits
SIC-MMAB: Synchronisation Involves Communication in Multiplayer Multi-Armed Bandits
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 synchronized exploration and deliberate collision-based communication | Decentralized multiplayer bandits with collision sensing · Synchronized static setting | exploration regret growth: exploration regret similar to the known centralized lower bound | Helped |
| Use synchronized collision communication, including its initialization and communication phases | SIC-MMAB · Synchronized static setting | total regret: The exploration term is $\sum_{k > M} \min \{ \frac{\log(T)}{\mu_{(M)} - \mu_{(k)}}, \sqrt{T \log(T)} \}$; communication | Mixed |
| Remove synchronization and use a communication-less protocol | SIC-MMAB dynamic algorithm · Dynamic decentralized, no sensing | regret growth: $\mathcal{O}\left( \frac{M^2K \log(T)}{\mu_{(M)}} + \frac{MK \log(T)}{\bar{\Delta}_{(M)}^2} \right)$ | Helped |
| Use SIC-MMAB rather than MCTopM | Synchronized synthetic Bernoulli bandits · Regret versus arm gap Δ | regret scaling with the gap: SIC-MMAB scales with $\Delta^{-1}$; MCTopM scales with $\Delta^{-2}$ | Helped |
| Use SIC-MMAB rather than MCTopM | Synchronized synthetic Bernoulli bandits · Larger arm gaps | regret | Hurt |
Closest papers by meaning
- Multi-Player Bandits – a Musical Chairs Approach (ICML 2016 · similarity 0.95)
- Decentralized Stochastic Multi-Player Multi-Armed Walking Bandits (AAAI 2023 · similarity 0.93)
- Decentralized Cooperative Stochastic Bandits (NeurIPS 2019 · similarity 0.92)
- Individual Regret in Cooperative Stochastic Multi-Armed Bandits (NeurIPS 2025 · similarity 0.89)
- Distributed Multi-Agent Bandits Over Erdős-Rényi Random Networks (NeurIPS 2025 · similarity 0.89)
- Decentralized Scheduling with QoS Constraints: Achieving O(1) QoS Regret of Multi-Player Bandits (AAAI 2024 · similarity 0.88)
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.