Research map / Multi-agent systems and games / Cooperative multi-agent RL
Kernel Methods for Cooperative Multi-Agent Contextual 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 Eager-KernelUCB, incorporating observations as soon as they arrive instead of controlling delayed information with clique partitions | Coop-KernelUCB · Synthetic and real-world network benchmarks; linear and RBF settings | regret | Helped |
| Weight or otherwise account for agent similarity when sharing observations, rather than treating neighbors' observations as one's own | Naive Cooperation · Synthetic and real-world network benchmarks; linear and kernel settings | regret | Helped |
| Use Dist-KernelUCB's central-agent and peripheral-agent action-mimicking strategy instead of Coop-KernelUCB | Coop-KernelUCB · Erdos-Renyi network benchmark | regret | No clear effect |
| Use agent-similarity-aware cooperation instead of independent single-agent methods | Single-agent LinUCB, KernelUCB, and IGP-UCB baselines · Synthetic and real-world network benchmarks; linear and RBF settings | per-agent regret | Helped |
Closest papers by meaning
- Communication Efficient Distributed Learning for Kernelized Contextual Bandits (NeurIPS 2022 · similarity 0.92)
- Learning Kernelized Contextual Bandits in a Distributed and Asynchronous Environment (ICLR 2023 · similarity 0.90)
- Multi-Agent Learning with Heterogeneous Linear Contextual Bandits (NeurIPS 2023 · similarity 0.90)
- A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits (NeurIPS 2022 · similarity 0.89)
- Distributed Multi-Agent Bandits Over Erdős-Rényi Random Networks (NeurIPS 2025 · similarity 0.89)
- Finite-Time Frequentist Regret Bounds of Multi-Agent Thompson Sampling on Sparse Hypergraphs (AAAI 2024 · 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.