合作与竞争：进化多智能体强化学习的群集
Cooperation and Competition: Flocking with Evolutionary Multi-Agent Reinforcement Learning
摘要：
在多智能体系统中，群集是一个非常具有挑战性的问题;传统的群集方法还需要对环境的完整了解和精确的控制模型。在本文中，我们提出了进化多智能体强化学习（EMARL）的群集任务，一个混合算法，结合合作和竞争，很少的先验知识。在合作方面，根据boids模型设计了集群任务的奖励。为了竞争，将适应度高的Agent设计为高级Agent，适应度低的Agent设计为低级Agent，让低级Agent随机继承高级Agent的参数。为了加强竞争，我们还设计了一个进化选择机制，显示在集群任务的信用分配有效。在一系列具有挑战性和自我对比的基准测试中的实验结果表明，EMARL显著优于完全竞争或合作方法。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
