Research map / Multi-agent systems and games / Cooperative multi-agent RL
Collective Online Learning of Gaussian Processes in Massive Multi-Agent Systems
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 |
|---|---|---|---|
| Fuse agents' local GP models with COOL-GP | COOL-GP · SYNTHETIC | predictive accuracy | Helped |
| Fuse agents' local GP models with COOL-GP | COOL-GP · AIMPEAK | predictive accuracy | Helped |
| Fuse local models across agents with different amounts of data | AIMPEAK agents A1 and A2 · AIMPEAK | RMSE | Helped |
| Fuse a data-rich agent's model with a conservative agent's model | AIMPEAK agent A2 · AIMPEAK | RMSE | Helped |
| Use decentralized neighborhood message passing instead of direct transmission to a central server | COOL-GP · AIMPEAK | post-fusion performance under transmission loss | Helped |
| Increase the amount of collected data | COOL-GP · SYNTHETIC and AIMPEAK | marginal gain from fusion | Hurt |
| Fuse agents' models using decentralized message passing | COOL-GP · AIRLINE | post-fusion RMSE variation across agents | Helped |
Closest papers by meaning
- Asynchronous Distributed Gaussian Process Regression (AAAI 2025 · similarity 0.85)
- Does Worst-Performing Agent Lead the Pack? Analyzing Agent Dynamics in Unified Distributed SGD (NeurIPS 2024 · similarity 0.84)
- Scalable Decentralized Algorithms for Online Personalized Mean Estimation (AAAI 2025 · similarity 0.83)
- Conditioning Gaussian Processes on Almost Anything (NeurIPS 2026 · similarity 0.83)
- MADiff: Offline Multi-agent Learning with Diffusion Models (NeurIPS 2024 · similarity 0.83)
- Learning Decentralized Partially Observable Mean Field Control for Artificial Collective Behavior (ICLR 2024 · similarity 0.83)
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.