A Survey of Multi-Agent Deep Reinforcement Learning with Communication

TL;DR

This survey reviews recent advances in multi-agent deep reinforcement learning with communication, classifies approaches along nine dimensions, and suggests future research directions for designing communication strategies among agents.

Contribution

It provides a systematic classification framework for Comm-MADRL approaches and identifies trends and future directions in the field.

Findings

Identification of 9 key dimensions for analyzing Comm-MADRL methods

Projection of existing works into a multi-dimensional space reveals trends

Proposes novel combinations of dimensions for future research

Abstract

Communication is an effective mechanism for coordinating the behaviors of multiple agents, broadening their views of the environment, and to support their collaborations. In the field of multi-agent deep reinforcement learning (MADRL), agents can improve the overall learning performance and achieve their objectives by communication. Agents can communicate various types of messages, either to all agents or to specific agent groups, or conditioned on specific constraints. With the growing body of research work in MADRL with communication (Comm-MADRL), there is a lack of a systematic and structural approach to distinguish and classify existing Comm-MADRL approaches. In this paper, we survey recent works in the Comm-MADRL field and consider various aspects of communication that can play a role in designing and developing multi-agent reinforcement learning systems. With these aspects in mind, we propose 9 dimensions along which Comm-MADRL approaches can be analyzed, developed, and compared. By projecting existing works into the multi-dimensional space, we discover interesting trends. We also propose some novel directions for designing future Comm-MADRL systems through exploring possible combinations of the dimensions.