Biases for Emergent Communication in Multi-agent Reinforcement Learning

Abstract

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.

arXiv commentAccepted at NeurIPS 2019

Cited by in corpus (13)

• Emergent Multi-Agent Communication in the Deep Learning Era
• Emergent Language: A Survey and Taxonomy
• Emergent Discrete Communication in Semantic Spaces
• Quasi-Equivalence Discovery for Zero-Shot Emergent Communication
• Emergent Graphical Conventions in a Visual Communication Game
• MARL with General Utilities via Decentralized Shadow Reward Actor-Critic
• Inter-Level Cooperation in Hierarchical Reinforcement Learning
• Correcting Experience Replay for Multi-Agent Communication
• Exploring Zero-Shot Emergent Communication in Embodied Multi-Agent Populations
• Multi-lingual agents through multi-headed neural networks
• Negotiating Team Formation Using Deep Reinforcement Learning
• Self-play for Data Efficient Language Acquisition
• Emergent Communication with World Models