Implementation of Q - Learning algorithm for solving maze problem

• Published in: 2011 Proceedings of the 34th International Convention MIPRO pp. 1619 - 1622
• Main Authors: Osmankovic, D., Konjicija, S.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.05.2011
• Subjects: agent; Artificial intelligence; machine intelligence; maze; reinforcement learning

Machine learning is very important in several fields ranging from control systems to data mining. This paper presents Q - Learning implementation for abstract graph models with maze solving (finding the trajectory out of the maze) taken as example of graph problem. The paper consists of conversion o...