Self-organizing neural networks integrating domain knowledge and reinforcement learning

• المؤلفون الرئيسيون: TENG, Teck-Hou, TAN, Ah-hwee, ZURADA, Jacek M.
• التنسيق: text
• اللغة: English
• منشور في: Institutional Knowledge at Singapore Management University 2015
• الموضوعات: Adaptive resonance theory (ART); domain knowledge; reinforcement learning (RL); self-organizing neural networks; Computer and Systems Architecture; Databases and Information Systems; OS and Networks
• الوصول للمادة أونلاين: https://ink.library.smu.edu.sg/sis_research/5236; https://ink.library.smu.edu.sg/context/sis_research/article/6239/viewcontent/Self_Organizing_Neural_Network_Integrating_Domain_Knowledge_and_Reinforcement_Learning___TNNLS_2014.pdf

The use of domain knowledge in learning systems is expected to improve learning efficiency and reduce model complexity. However, due to the incompatibility with knowledge structure of the learning systems and real-time exploratory nature of reinforcement learning (RL), domain knowledge cannot be ins...