Entropy-based local fitnesses for evolutionary multiagent systems
Entropy-based local fitnesses for evolutionary multiagent systems
复制标题
进化多智能体系统的基于熵的局部适应度
DOI：
10.1145/3520304.3529035
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Tumer, Kagan
中科院分区：
文献类型：
--
作者：
Aydeniz, Ayhan Alp;Nickelson, Anna;Tumer, Kagan
进化多智能体系统已经成功地应用于许多真实的世界问题，包括搜索和救援以及海洋探索。然而，随着代理数量的增加，在这样的问题中，评估功能捕获一个单独的代理的健身越来越不准确。其结果是，代理人采取一小部分可接受的行为，既不是最佳的，也不强大的环境变化或队友失败。适应度塑造、内在适应度或多适应度学习缓解了这些问题中的一些，但通常需要领域知识或评估函数的函数形式。在本文中，我们介绍了基于熵的局部适应度（EBLF），产生不同的行为代理和产生强大的团队行为，而不需要环境知识。EBLF的主要贡献是将密集的、基于熵的适应度注入到代理的进化中，而不干扰稀疏的、高级的系统评估函数。我们的研究结果表明，代理使用EBLF学习新的技能，在困难的环境中，稀疏的反馈，而不需要领域知识。此外，EBLF产生了新的团队级别的行为，这些行为不是由人类操作员定义的，但有利于强大的团队绩效。
Evolutionary multiagent systems have been successfully applied to many real world problems, including search and rescue and ocean exploration. However, as the number of agents increases in such problems, the evaluation function captures an individual agent's fitness less and less accurately. As a consequence, agents adopt a small set of acceptable behaviors that are neither optimal nor robust to environmental changes or teammate failures. Fitness shaping, intrinsic fitnesses, or multi-fitness learning alleviate some of these concerns but generally require domain knowledge or the functional form of the evaluation function. In this paper, we introduce Entropy-Based Local Fitnesses (EBLFs) that generate diverse behaviors for agents and produce robust team behaviors without requiring environmental knowledge. The key contribution of EBLFs is to inject a dense, entropy-based fitness into the agents' evolution without interfering with the sparse, high-level system evaluation function. Our results show that the agents using EBLFs learn new skills in difficult environments with sparse feedback without requiring domain knowledge. In addition, EBLFs generated new team-level behaviors that were not defined by a human operator, but beneficial to robust team performance.
影响因子：
1.6
作者：
Cliff, Dave;Harvey, Inman;Husbands, Phil
通讯作者：
Husbands, Phil