Symbiotic Evolution of Neural Networks in Sequential Decision Tasks

神经网络在顺序决策任务中的共生进化

• 批准号: 9504317
• 负责人: Risto Miikkulainen
• 金额: $ 25.95万
• 依托单位: University of Texas at Austin
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 1995
• 资助国家: 美国
• 起止时间: 1995-09-15 至 1999-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9504317&HistoricalAwards=false
• 关键词: Symbiotic; Evolution; Neural; Networks; Sequential

Sequential decision tasks appear in many real-world domains, including control, resource allocation, routing, and scheduling. The objective of this project is to develop a new approach to sequential decision making based on symbiotic evolution of neural networks. In symbiotic evolution, a population of neurons are evolved with genetic algorithms to cooperate and form decision-making networks. Diversity is maintained in the population as part of the task and the system can find good solutions efficiently even in difficult tasks with sparse reinforcement. In the proposed project, symbiotic evolution will be analyzed both theoretically and experimentally, the algorithm will be further developed and applied to complex real-world domains such as local-area network management, and a practical high-level interface will be developed that will allow rapid application of the method to new domains. The main scientific contributions of the research are expected to be: (1) a novel, powerful method for extracting and encoding problem-specific knowledge automatically for sequential decision making, and (2) a thorough understanding of the role of diversity and cooperation in genetic algorithms. The development of the general application interface should also benefit many practical fields, including control engineering, military science, and operations management. The main hypotheses to be tested are: (1) Pattern recognition and generalization capabilities of neural networks can be used to implement effective and robust sequential decision making strategies;(2) Genetic algorithms can discover powepful problem-specific decision-making strategies even under sparse reinforcement; 3) By making population diversity an essential part of the task, symbiotic evolution can develop solutions to harder problems and do it more efficiently than standard genetic algorithms.

顺序决策任务出现在许多现实领域中，包括控制、资源分配、路由和调度。 该项目的目标是开发一种基于神经网络共生进化的顺序决策的新方法。 在共生进化中，一群神经元通过遗传算法进化来合作并形成决策网络。 作为任务的一部分，群体的多样性得以维持，即使在强化稀疏的困难任务中，系统也能有效地找到好的解决方案。在拟议的项目中，将从理论上和实验上分析共生进化，进一步开发该算法并将其应用于复杂的现实世界领域，例如局域网管理，并将开发一个实用的高级接口，该接口将允许该方法快速应用于新领域。 该研究的主要科学贡献预计将是：（1）一种新颖、强大的方法，用于自动提取和编码特定问题的知识以进行顺序决策，以及（2）全面了解多样性与合作在遗传中的作用算法。 通用应用接口的开发也应该有利于许多实际领域，包括控制工程、军事科学和运营管理。 待检验的主要假设是：（1）神经网络的模式识别和泛化能力可用于实现有效且鲁棒的顺序决策策略；（2）遗传算法即使在稀疏的情况下也能发现强大的针对特定问题的决策策略加强; 3）通过使种群多样性成为任务的重要组成部分，共生进化可以开发更困难问题的解决方案，并且比标准遗传算法更有效。