Cooperation and Competition: Flocking with Evolutionary Multi-Agent Reinforcement Learning
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.
Cite
@article{arxiv.2209.04696,
title = {Cooperation and Competition: Flocking with Evolutionary Multi-Agent Reinforcement Learning},
author = {Yunxiao Guo and Xinjia Xie and Runhao Zhao and Chenglan Zhu and Jiangting Yin and Han Long},
journal= {arXiv preprint arXiv:2209.04696},
year = {2022}
}
Comments
We misplaced Fig.5 (b) on Page 11 ( This figure is from early experiments with poor results). We failed to resubmit, so we want to revise the whole paper by this chance