mlsanityData to 7 Oct 2026

ClusterComm: Discrete Communication in Decentralized MARL using Internal Representation Clustering

arXiv 2401.03504 ↗First posted 7 Jan 2024cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

In the realm of Multi-Agent Reinforcement Learning (MARL), prevailing approaches exhibit shortcomings in aligning with human learning, robustness, and scalability. Addressing this, we introduce ClusterComm, a fully decentralized MARL framework where agents communicate discretely without a central control unit. ClusterComm utilizes Mini-Batch-K-Means clustering on the last hidden layer's activations of an agent's policy network, translating them into discrete messages. This approach outperforms no communication and competes favorably with unbounded, continuous communication and hence poses a simple yet effective strategy for enhancing collaborative task-solving in MARL.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 18 of its 34 references that are in the map. First posted on arXiv 7 Jan 2024.

Builds on

18 of 34 references.

References · 18

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,519
  3. 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 903
  4. 2016Learning to Communicate with Deep Multi-Agent Reinforcement Learningcited by 561
  5. 2016Learning Multiagent Communication with Backpropagationcited by 355
  6. 2016Safe, Multi-Agent, Reinforcement Learning for Autonomous Drivingcited by 301
  7. 2017Emergence of Grounded Compositional Language in Multi-Agent Populationscited by 257
  8. 2017NormFace: L2 Hypersphere Embedding for Face Verificationcited by 237
  9. 2020Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Taskscited by 207
  10. 2018TarMAC: Targeted Multi-Agent Communicationcited by 201
  11. 2018Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agentscited by 189
  12. 2019Transformers without Tears: Improving the Normalization of Self-Attentioncited by 153
6 more
  1. 2020Shared Experience Actor-Critic for Multi-Agent Reinforcement Learningcited by 114
  2. 2019Biases for Emergent Communication in Multi-agent Reinforcement Learningcited by 48
  3. 2021Learning to Ground Multi-Agent Communication with Autoencoderscited by 37
  4. 2018Compositional Obverter Communication Learning From Raw Visual Inputcited by 30
  5. 2022FCMNet: Full Communication Memory Net for Team-Level Cooperation in Multi-Agent Systemscited by 7
  6. 2022An Analysis of Discretization Methods for Communication Learning with Multi-Agent Reinforcement Learningcited by 6

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025LEED: A Highly Efficient and Scalable LLM-Empowered Expert Demonstrations Framework for Multi-Agent Reinforcement Learningcited by 6