Deep Reinforcement Learning for Multi-Agent Interaction

TL;DR

This paper reviews advances in deep reinforcement learning for multi-agent systems, focusing on scalable coordination, communication, and reasoning, highlighting open challenges and future research directions.

Contribution

It provides a comprehensive overview of recent research in multi-agent deep reinforcement learning and discusses key open problems in the field.

Findings

Progress in scalable multi-agent policy learning

Development of inter-agent communication methods

Identification of open challenges and future directions

Abstract

The development of autonomous agents which can interact with other agents to accomplish a given task is a core area of research in artificial intelligence and machine learning. Towards this goal, the Autonomous Agents Research Group develops novel machine learning algorithms for autonomous systems control, with a specific focus on deep reinforcement learning and multi-agent reinforcement learning. Research problems include scalable learning of coordinated agent policies and inter-agent communication; reasoning about the behaviours, goals, and composition of other agents from limited observations; and sample-efficient learning based on intrinsic motivation, curriculum learning, causal inference, and representation learning. This article provides a broad overview of the ongoing research portfolio of the group and discusses open problems for future directions.