mlsanityData to 7 Oct 2026

Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks

arXiv 1602.02672 ↗First posted 8 Feb 2016cs.AI cs.LGcited by 21

Not on the map. Why?

Abstract (arXiv)

We propose deep distributed recurrent Q-networks (DDRQN), which enable teams of agents to learn to solve communication-based coordination tasks. In these tasks, the agents are not given any pre-designed communication protocol. Therefore, in order to successfully communicate, they must first automatically develop and agree upon their own communication protocol. We present empirical results on two multi-agent learning problems based on well-known riddles, demonstrating that DDRQN can successfully solve such tasks and discover elegant communication protocols to do so. To our knowledge, this is the first time deep reinforcement learning has succeeded in learning communication protocols. In addition, we present ablation experiments that confirm that each of the main components of the DDRQN architecture are critical to its success.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Feb 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 3; 2023: 4; 2024: 2; 2025: 3; 2026: 3.

21 papers.

Sort:

By area:

  1. 2021Learning to Ground Multi-Agent Communication with Autoencoderscited by 37
  2. 2022Deep Transformer Q-Networks for Partially Observable Reinforcement Learningcited by 35
  3. 2025A Comprehensive Survey on Multi-Agent Cooperative Decision-Making: Scenarios, Approaches, Challenges and Perspectivescited by 27
  4. 2021Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Surveycited by 23
  5. 2021Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agentscited by 19
  6. 2024Generative Emergent Communication: Large Language Model is a Collective World Modelcited by 15
  7. 2026The Five Ws of Multi-Agent Communication: Who Talks to Whom, When, What, and Why -- A Survey from MARL to Emergent Language and LLMscited by 10
  8. 2021Emergence of Theory of Mind Collaboration in Multiagent Systemscited by 8
  9. 2023Approximate information state based convergence analysis of recurrent Q-learningcited by 5
  10. 2024Behavior-Inspired Neural Networks for Relational Inferencecited by 4
  11. 2021Deep Reinforcement Learning for Demand Driven Services in Logistics and Transportation Systems: A Surveycited by 3
  12. 2023CAMMARL: Conformal Action Modeling in Multi Agent Reinforcement Learningcited by 3
9 more
  1. 2023Visual Spatial Attention and Proprioceptive Data-Driven Reinforcement Learning for Robust Peg-in-Hole Task Under Variable Conditionscited by 2
  2. 2022Resilient robot teams: a review integrating decentralised control, change-detection, and learningcited by 1
  3. 2023Model-free Motion Planning of Autonomous Agents for Complex Tasks in Partially Observable Environmentscited by 1
  4. 2026GlossoGen: Emergent Language in Complex Multi-Agent LLM Interactionscited by 1
  5. 2021Socially Supervised Representation Learning: the Role of Subjectivity in Learning Efficient Representationscited by 0
  6. 2022A Decentralized Communication Framework based on Dual-Level Recurrence for Multi-Agent Reinforcement Learningcited by 0
  7. 2025Bi-directional Recurrence Improves Transformer in Partially Observable Markov Decision Processescited by 0
  8. 2025Adaptive Event-Triggered Policy Gradient for Multi-Agent Reinforcement Learningcited by 0
  9. 2026Provably Optimal Learning Algorithms for Assistance Gamescited by 0