Research map / Multi-agent systems and games / Cooperative multi-agent RL
Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation
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 asynchronous, determinant-triggered communication instead of synchronous round-robin communication | Cooperative linear MDP learning · Linear MDPs | communication complexity: $d H M^3$ -> $d H M^2$ | Helped |
| Use asynchronous communication while preserving the regret guarantee | Cooperative linear MDP learning · Linear MDPs | regret: $d^{3/2} H^2 \sqrt{K}$ -> $d^{3/2}H^2\sqrt{K} $ | No clear effect |
| Restrict communication complexity to less than $dM/11400$ | Any cooperative linear-MDP algorithm · Linear MDPs with $d,H\ge 2$ and $K\ge dM$ | regret lower bound: $\Omega(H\sqrt{dMK})$ | Hurt |
| Set the communication-trigger parameter to $\alpha = 1/M^2$ and $\lambda = 1$ | Async-Coop-LSVI-UCB · Linear MDPs | communication complexity: $\tilde{\mathcal{O}}(dH(M+1/\alpha))$ -> $\tilde{\mathcal{O}}(dHM^2)$ | Helped |
Closest papers by meaning
- Multi-Agent Reinforcement Learning with Communication-Constrained Priors (NeurIPS 2025 · similarity 0.89)
- Communication-Efficient Actor-Critic Methods for Homogeneous Markov Games (ICLR 2022 · similarity 0.89)
- Efficient Communication in Multi-Agent Reinforcement Learning with Implicit Consensus Generation (AAAI 2025 · similarity 0.88)
- Randomized Exploration in Cooperative Multi-Agent Reinforcement Learning (NeurIPS 2024 · similarity 0.88)
- Exponential Topology-enabled Scalable Communication in Multi-agent Reinforcement Learning (ICLR 2025 · similarity 0.88)
- Learning Joint Behaviors with Large Variations (AAAI 2025 · 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.