Title :
Learning in proximity
Author :
Jamalian, A.H. ; Rezvani, R. ; Mehrabi, SH
Author_Institution :
Andisheh Branch, Sama Tech. & Vocational Training Coll., Andisheh, Iran
Abstract :
In most articles about machine learning, particularly in reinforcement learning, a learning system interacts with an unknown environment and tries to improve its performance (receiving fewer penalties) according to feedback from environment as reinforcement signals. In this paper we show how a learning system can learn to interact with environment from an experienced agent (experienced learning system). Simulation results show that when a learning system learns from an experienced agent before exposure, it can interact better than a same raw learning system and receive fewer penalties from the environment.
Keywords :
learning (artificial intelligence); learning systems; machine learning system; proximity learning; reinforcement learning; reinforcement signals; Bismuth; Learning automata; Learning Automata; Machine Learning; Proximity; Reinforcement Learning;
Conference_Titel :
Cognitive Informatics & Cognitive Computing (ICCI*CC ), 2011 10th IEEE International Conference on
Conference_Location :
Banff, AB
Print_ISBN :
978-1-4577-1695-9
DOI :
10.1109/COGINF.2011.6016127
