Emergence, Not Bandwidth: Physical Coupling and the Limits of Learned Multi-Agent Communication
cs.LG, cs.MA, cs.RO
Submitted: 2026-09-28
Updated: 2026-09-29
Terminology
Sources
- Bandwidth-Efficient Multi-Agent Communication through Information Bottleneck and Vector Quantization
- Communicating Plans, Not Percepts: Scalable Multi-Agent Coordination with Embodied World Models
- Learning what to say and how precisely: Efficient Communication via Differentiable Discrete Communication Learning
- Proximal Policy Optimization Algorithms
- An Analysis of Discretization Methods for Communication Learning with Multi-Agent Reinforcement Learning
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks