Reinforcement-Learning Connectionist Systems (Computer and Information Science)

类似神经元的处理单元组成的网络， 联结主义系统，有着有趣的计算特性 这使得它们对心理建模和 人工智能的潜在应用。 最近 研究已经导致了一些有前途的学习算法， 这样的网络。 该项目通过开发一种 设计算法的数学上有根据的方法 对于强化学习的特殊问题， 随机单位的联结主义网络 特别 算法被开发用于学习具有 重要的时间部分，例如 持续时间未知的反馈延迟或涉及 识别或产生时变信号。 这些 算法需要承认一个合适的在线 学习发生在操作过程中的实现， 系统 除了在这种理论上取得进展外， 算法，该项目涉及实现更有前途的 候选人和评估他们在模拟中的表现 实验 评价的主要标准是学习 有效性和收敛于次优的可能性 states. 此外，本项目还探讨了 这些算法可以解决人工智能中的特定问题 和机器人技术， 解决这些问题。 这些问题包括语音识别和 自适应感觉运动控制

Networks of neuron-like processing units, called connectionist systems, have interesting computational properties making them attractive for both psychological modeling and potential application in artificial intelligence. Recent research has led to some promising algorithms for learning in such networks. This project advances such research by developing a mathematically well-founded approach to the design of algorithms for the particular problem of reinforcement learning in connectionist networks of stochastic units. Particular algorithms are developed for learning problems having an important temporal component, such as control problems with feedback delays of unknown duration or problems involving recognition or production of time-varying signals. These algorithms are required to admit a suitable on-line implementation, in which the learning occurs within the operating system. In addition to making advances in the theory of such algorithms, this project involves implementing the more promising candidates and evaluating their performance in simulation experiments. Primary criteria for evaluation are learning efficiency and suspectibility to convergence to suboptimal states. In addition, this project explores the applicability of such algorithms to specific problems in artificial intelligence and robotics through the study of suitably scaled-down versions of these problems. Such problems include speech recognition and adaptive sensorimotor control.