Communication Gain and Delay Cost Under Cross-Timestep Delays in Cooperative Multi-Agent Reinforcement Learning

arXiv:2604.03785 · cs.AI, cs.MA · Submitted 2026-04-04 · Read on arXiv

cs.AI, cs.MA

Submitted: 2026-04-04

Updated: 2026-09-27

Terminology

• Actor — 23× in this paper · explained in 3 episodes
• Aggregation — 20× in this paper · explained in 1 episode
• Reinforcement Learning — 18× in this paper · explained in 4 episodes
• Robustness — 14× in this paper · explained in 5 episodes
• Predator Prey — 11× in this paper
• Ablation — 10× in this paper · explained in 1 episode
• Communication Gain and Delay Cost — 9× in this paper
• Cooperative Navigation — 7× in this paper
• Cooperation — 4× in this paper · explained in 2 episodes
• Alignment — 3× in this paper · explained in 1 episode
• Guided attention — 3× in this paper · explained in 2 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• CGDC-guided Attentional Message Aggregator — 2× in this paper
• Consistency — 2× in this paper · explained in 3 episodes
• Delay Communication Objective Selector — 2× in this paper
• Generalization — 2× in this paper · explained in 13 episodes
• Multi-Agent System — 2× in this paper · explained in 6 episodes
• Observation Trajectory Generator — 2× in this paper
• StarCraft Multi-Agent Challenge — 2× in this paper
• Abstraction — 1× in this paper · explained in 1 episode
• Activation Function — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Adversarial Robustness — 1× in this paper · explained in 3 episodes
• Deep Reinforcement Learning — 1× in this paper · explained in 2 episodes
• Distribution Shift — 1× in this paper · explained in 5 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Model-Agnostic — 1× in this paper · explained in 2 episodes
• Multi-Agent Particle Environment — 1× in this paper
• Multi-Agent Reinforcement Learning (MARL) — 1× in this paper · explained in 4 episodes
• Multi-agent Collaboration — 1× in this paper · explained in 2 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• Redundancy — 1× in this paper · explained in 2 episodes

Sources

• Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection