Learning to Communicate with Deep Multi-Agent Reinforcement Learning

2016-05-21 · NeurIPS 2016 12 · Jakob N. Foerster, Yannis M. Assael, Nando de Freitas, Shimon Whiteson

We consider the problem of multiple agents sensing and acting in environments with the goal of maximising their shared utility. In these environments, agents must learn communication protocols in order to share information that is needed to solve the tasks. By embracing deep neural networks, we are able to demonstrate end-to-end learning of protocols in complex environments inspired by communication riddles and multi-agent computer vision problems with partial observability. We propose two approaches for learning in these domains: Reinforced Inter-Agent Learning (RIAL) and Differentiable Inter-Agent Learning (DIAL). The former uses deep Q-learning, while the latter exploits the fact that, during learning, agents can backpropagate error derivatives through (noisy) communication channels. Hence, this approach uses centralised learning but decentralised execution. Our experiments introduce new environments for studying the learning of communication protocols and present a set of engineering innovations that are essential for success in these domains.

📄 PDF Abstract BibTeX arXiv:1605.06676

Code (3)

emiliojorge/Inventing-a-Grounded-Language

iassael/learning-to-communicate pytorch

sharan-dce/DIAL-switch tf

Tasks

Multi-agent Reinforcement LearningQ-Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

ACCNet: Actor-Coordinator-Critic Net for "Learning-to-Communicate" with Deep Multi-agent Reinforcement Learning

2017-06-10 · Hangyu Mao, Zhibo Gong, Yan Ni, Zhen Xiao

Communication is a critical factor for the big multi-agent world to stay organized and productive. Typically, most previous multi-agent "learning-to-communicate" studies try to predefine the communication protocols or us…

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Toward Collaborative Reinforcement Learning Agents that Communicate Through Text-Based Natural Language

2021-07-20 · Kevin Eloff, Herman A. Engelbrecht

Communication between agents in collaborative multi-agent settings is in general implicit or a direct data stream. This paper considers text-based natural language as a novel form of communication between multiple agents…

Navigate reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Effective Communications: A Joint Learning and Communication Framework for Multi-Agent Reinforcement Learning over Noisy Channels

2021-01-02 · Tze-Yang Tung, Szymon Kobus, Joan Roig Pujol, Deniz Gunduz

We propose a novel formulation of the "effectiveness problem" in communications, put forth by Shannon and Weaver in their seminal work [2], by considering multiple agents communicating over a noisy channel in order to ac…

Deep Reinforcement Learning Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning (RL)

Learning to Communicate in Multi-Agent Reinforcement Learning for Autonomous Cyber Defence

2025-07-19 · Faizan Contractor, Li Li, Ranwa Al Mallah arxiv

Popular methods in cooperative Multi-Agent Reinforcement Learning with partially observable environments typically allow agents to act independently during execution, which may limit the coordinated effect of the trained…

Multi-agent Reinforcement Learning

Learning to Communicate in Multi-Agent Reinforcement Learning : A Review

2019-11-13 · Mohamed Salah Zaïem, Etienne Bennequin

We consider the issue of multiple agents learning to communicate through reinforcement learning within partially observable environments, with a focus on information asymmetry in the second part of our work. We provide a…