Cooperation and Competition: Flocking with Evolutionary Multi-Agent Reinforcement Learning

TL;DR

This paper introduces EMARL, a hybrid multi-agent reinforcement learning approach for flocking that combines cooperation and competition, enabling effective learning with minimal prior knowledge and outperforming traditional methods.

Contribution

The paper presents a novel hybrid EMARL algorithm that integrates cooperative reward design and competitive evolutionary selection for flocking tasks.

Findings

EMARL significantly outperforms pure cooperation or competition methods.

The evolutionary selection mechanism improves credit assignment.

Agents inherit parameters stochastically, enhancing learning efficiency.

Abstract

Flocking is a very challenging problem in a multi-agent system; traditional flocking methods also require complete knowledge of the environment and a precise model for control. In this paper, we propose Evolutionary Multi-Agent Reinforcement Learning (EMARL) in flocking tasks, a hybrid algorithm that combines cooperation and competition with little prior knowledge. As for cooperation, we design the agents' reward for flocking tasks according to the boids model. While for competition, agents with high fitness are designed as senior agents, and those with low fitness are designed as junior, letting junior agents inherit the parameters of senior agents stochastically. To intensify competition, we also design an evolutionary selection mechanism that shows effectiveness on credit assignment in flocking tasks. Experimental results in a range of challenging and self-contrast benchmarks demonstrate that EMARL significantly outperforms the full competition or cooperation methods.