Multi-Agent Deep Reinforcement Learning with Human Strategies

TL;DR

This paper presents a multi-agent deep reinforcement learning approach that incorporates human strategies to enhance exploration, demonstrated through a new environment showing improved cooperative performance.

Contribution

It introduces a novel method integrating human strategies into multi-agent deep reinforcement learning and develops a new environment for testing such algorithms.

Findings

Significant performance improvements with human strategies

Effective cooperation among multiple agents

The environment serves as a versatile testbed platform

Abstract

Deep learning has enabled traditional reinforcement learning methods to deal with high-dimensional problems. However, one of the disadvantages of deep reinforcement learning methods is the limited exploration capacity of learning agents. In this paper, we introduce an approach that integrates human strategies to increase the exploration capacity of multiple deep reinforcement learning agents. We also report the development of our own multi-agent environment called Multiple Tank Defence to simulate the proposed approach. The results show the significant performance improvement of multiple agents that have learned cooperatively with human strategies. This implies that there is a critical need for human intellect teamed with machines to solve complex problems. In addition, the success of this simulation indicates that our multi-agent environment can be used as a testbed platform to develop and validate other multi-agent control algorithms.