Knowledge-based exploration for reinforcement learning in self-organizing neural networks

• Main Authors: TENG, Teck-Hou, TAN, Ah-hwee
• 格式: text
• 語言: English
• 出版: Institutional Knowledge at Singapore Management University 2012
• 主題: Reinforcement Learning; Self-Organizing Neural Network; Directed Exploration; Rule-Based System; Artificial Intelligence and Robotics; Databases and Information Systems
• 在線閱讀: https://ink.library.smu.edu.sg/sis_research/6275; https://ink.library.smu.edu.sg/context/sis_research/article/7278/viewcontent/Knowledge_based_Exploration___IAT_2012.pdf

Exploration is necessary during reinforcement learning to discover new solutions in a given problem space. Most reinforcement learning systems, however, adopt a simple strategy, by randomly selecting an action among all the available actions. This paper proposes a novel exploration strategy, known a...