Title :
Social Reinforcement Learning in Game Playing
Author :
Kiourt, C. ; Kalles, Dimitris
Author_Institution :
Sch. of Sci. & Technol., Hellenic Open Univ., Patras, Greece
Abstract :
In this work we discuss Social Reinforcement Learning on self-trained agents. We simulate social learning by implementing a tournament on an existing board game that utilizes reinforcement learning for playing and learning. The socially trained agents are compared to self-trained agents and their superior performance is noted. The findings and the infrastructure requirements mandate the development of a Social Reinforcement Learning Multi-Agent-Based Simulation platform.
Keywords :
computer games; learning (artificial intelligence); multi-agent systems; board game; game playing; multiagent-based simulation platform; self-trained agent; social reinforcement learning; socially trained agent; Artificial intelligence; Conferences; Board Games; Multi-Agent Systems; Reinforcement Learning; Social Learning;
Conference_Titel :
Tools with Artificial Intelligence (ICTAI), 2012 IEEE 24th International Conference on
Conference_Location :
Athens
Print_ISBN :
978-1-4799-0227-9
DOI :
10.1109/ICTAI.2012.51
