Biases for Emergent Communication in Multi-agent Reinforcement Learning

2019-12-11 · NeurIPS 2019 12 · Tom Eccles, Yoram Bachrach, Guy Lever, Angeliki Lazaridou, Thore Graepel

We study the problem of emergent communication, in which language arises because speakers and listeners must communicate information in order to solve tasks. In temporally extended reinforcement learning domains, it has proved hard to learn such communication without centralized training of agents, due in part to a difficult joint exploration problem. We introduce inductive biases for positive signalling and positive listening, which ease this problem. In a simple one-step environment, we demonstrate how these biases ease the learning problem. We also apply our methods to a more extended environment, showing that agents with these inductive biases achieve better performance, and analyse the resulting communication protocols.

📄 PDF Abstract BibTeX arXiv:1912.05676

Code (0)

등록된 구현이 없습니다.

Tasks

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

Generalizing Emergent Communication

2020-01-06 · Thomas A. Unger, Elia Bruni

We converted the recently developed BabyAI grid world platform to a sender/receiver setup in order to test the hypothesis that established deep reinforcement learning techniques are sufficient to incentivize the emergenc…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+1

AI Mother Tongue: Self-Emergent Communication in MARL via Endogenous Symbol Systems

2025-07-07 · Hung Ming Liu arxiv

In Decentralized Multi-Agent Reinforcement Learning (MARL), the development of Emergent Communication has long been constrained by the ``Joint Exploration Dilemma'', leading agents to fall into a ``Communication Vacuum E…

Multi-agent Reinforcement Learning

Emergent Cooperation in Quantum Multi-Agent Reinforcement Learning Using Communication

2026-01-26 · Michael Kölle, Christian Reff, Leo Sünkel, Julian Hager 외 arxiv

Emergent cooperation in classical Multi-Agent Reinforcement Learning has gained significant attention, particularly in the context of Sequential Social Dilemmas (SSDs). While classical reinforcement learning approaches h…

Multi-agent Reinforcement Learning

Learning and communication pressures in neural networks: Lessons from emergent communication

2024-03-21 · Lukas Galke, Limor Raviv

Finding and facilitating commonalities between the linguistic behaviors of large language models and humans could lead to major breakthroughs in our understanding of the acquisition, processing, and evolution of language…

Language Acquisition Multi-agent Reinforcement Learning

Emergent Communication Protocol Learning for Task Offloading in Industrial Internet of Things

2024-01-23 · Salwa Mostafa, Mateus P. Mota, Alvaro Valcarce, Mehdi Bennis

In this paper, we leverage a multi-agent reinforcement learning (MARL) framework to jointly learn a computation offloading decision and multichannel access policy with corresponding signaling. Specifically, the base stat…

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning