Research map / Multi-agent systems and games / Cooperative multi-agent RL
DACOM: Learning Delay-Aware Communication for Multi-Agent Reinforcement Learning
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 |
|---|---|---|---|
| Adapt waiting time to network state with TimeNet | DACOM · Cooperative Navigation and Predator-Prey | normalized reward | Helped |
| Adapt communication waiting time to delay | DACOM · Traffic Control intersection | collision rate | Helped |
| Adapt communication waiting time to delay | DACOM · Traffic Control intersection | arrival rate | Helped |
| Use communication without accounting for communication delay | communication-based MARL · Delay-sensitive tasks and high-delay environments | reward | Hurt |
| Use a fixed waiting timer instead of adapting it to network conditions | ACML · Low-delay environments (approximately 10%) | reward | Hurt |
| Use communication rather than no communication | DACOM · Predator-Prey, mean delay ratio greater than 70% | reward | No clear effect |
| Use adaptive delay-aware communication | DACOM · SMAC 3m and 8m | win rate | No clear effect |
| Use a fixed timer to limit waiting | ACML and ATOC · Increasing communication delays | reward | Helped |
Closest papers by meaning
- CoDe: Communication Delay-Tolerant Multi-Agent Collaboration via Dual Alignment of Intent and Timeliness (AAAI 2025 · similarity 0.89)
- Multi-Agent Reinforcement Learning with Communication-Constrained Priors (NeurIPS 2025 · similarity 0.88)
- Efficient Communication in Multi-Agent Reinforcement Learning with Implicit Consensus Generation (AAAI 2025 · similarity 0.88)
- Exponential Topology-enabled Scalable Communication in Multi-agent Reinforcement Learning (ICLR 2025 · similarity 0.88)
- Rainbow Delay Compensation: A Multi-Agent Reinforcement Learning Framework for Mitigating Observation Delays (NeurIPS 2025 · similarity 0.87)
- Bridging Training and Execution via Dynamic Directed Graph-Based Communication in Cooperative Multi-Agent Systems (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.