# Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applications

## TL;DR

This paper reviews deep reinforcement learning methods for multi-agent systems, discussing challenges, solutions, and applications, and aims to guide future research in developing more robust multi-agent learning techniques.

## Contribution

It provides a comprehensive survey of multi-agent deep RL approaches, analyzing their merits, demerits, and applications, highlighting key challenges and potential future directions.

## Key findings

- Analysis of non-stationarity and partial observability issues
- Comparison of multi-agent training schemes and transfer learning methods
- Discussion of applications in real-world multi-agent problems

## Abstract

Reinforcement learning (RL) algorithms have been around for decades and employed to solve various sequential decision-making problems. These algorithms however have faced great challenges when dealing with high-dimensional environments. The recent development of deep learning has enabled RL methods to drive optimal policies for sophisticated and capable agents, which can perform efficiently in these challenging environments. This paper addresses an important aspect of deep RL related to situations that require multiple agents to communicate and cooperate to solve complex tasks. A survey of different approaches to problems related to multi-agent deep RL (MADRL) is presented, including non-stationarity, partial observability, continuous state and action spaces, multi-agent training schemes, multi-agent transfer learning. The merits and demerits of the reviewed methods will be analyzed and discussed, with their corresponding applications explored. It is envisaged that this review provides insights about various MADRL methods and can lead to future development of more robust and highly useful multi-agent learning methods for solving real-world problems.