Research map / Bandits and online learning / Online convex optimization and games
One More Step Towards Reality: Cooperative Bandits with Imperfect Communication
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 |
|---|---|---|---|
| Probabilistically discard incoming messages using agent-specific probabilities | RCL-LF · Irregular communication graphs | group regret | Helped |
| Use probabilistic message discarding | RCL-LF · Near-regular communication graphs | group regret | No clear effect |
| Incorporate incoming messages as soon as they are available despite stochastic delays | RCL-SD · Stochastic delays; bounded delays with expected delay 10 | group regret | Helped |
| Use delayed incorporation of messages | Delayed MP-UCB · Perfect communication; multi-star and random tree graphs | group regret | Helped |
| Use individual UCB1 instead of cooperative message-passing | RCL-AC comparison · Adversarial communication; varying corruption ε | group regret | Hurt |
| Use cooperative MP-UCB instead of RCL-AC | Adversarial communication · Adversarial communication; varying corruption ε | group regret | Hurt |
Closest papers by meaning
- Decentralized Cooperative Stochastic Bandits (NeurIPS 2019 · similarity 0.93)
- Decentralized Multi-Agent Linear Bandits with Safety Constraints (AAAI 2021 · similarity 0.91)
- Individual Regret in Cooperative Stochastic Multi-Armed Bandits (NeurIPS 2025 · similarity 0.91)
- Cooperative Multi-player Bandit Optimization (NeurIPS 2020 · similarity 0.90)
- Distributed Multi-Agent Bandits Over Erdős-Rényi Random Networks (NeurIPS 2025 · similarity 0.89)
- The Bandit Whisperer: Communication Learning for Restless Bandits (AAAI 2025 · similarity 0.87)
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.