Learning a super mario controller from examples of human play

Lee, G, Luo, M, Zambetta, F and Li, X 2014, 'Learning a super mario controller from examples of human play', in D. Liu (ed.) Proceedings of the 2014 IEEE Congress on Evolutionary Computation (CEC2014), Beijing, China, 6 - 11 July 2014, pp. 1-8.


Document type: Conference Paper
Collection: Conference Papers

Title Learning a super mario controller from examples of human play
Author(s) Lee, G
Luo, M
Zambetta, F
Li, X
Year 2014
Conference name CEC2014
Conference location Beijing, China
Conference dates 6 - 11 July 2014
Proceedings title Proceedings of the 2014 IEEE Congress on Evolutionary Computation (CEC2014)
Editor(s) D. Liu
Publisher IEEE
Place of publication United States
Start page 1
End page 8
Total pages 8
Abstract Imitating human-like behaviour in action games is a challenging but intriguing task in Artificial Intelligence research, with various strategies being employed to solve the human-like imitation problem. In this research we consider learning human-like behaviour via Markov decision processes without being explicitly given a reward function, and learning to perform the task by observing expert's demonstration. Individual players often have characteristic styles when playing the game, and this method attempts to find the behaviours which make them unique. During play sessions of Super Mario we calculate player's behaviour policies and reward functions by applying inverse reinforcement learning to the player's actions in game. We conduct an online questionnaire which displays two video clips, where one is played by a human expert and the other is played by the designed controller based on the player's policy. We demonstrate that by using apprenticeship learning via Inverse Reinforcement Learning, we are able to get an optimal policy which yields performance close to that of an human expert playing the game, at least under specific conditions.
Subjects Adaptive Agents and Intelligent Robotics
Virtual Reality and Related Simulation
DOI - identifier 10.1109/CEC.2014.6900246
Copyright notice © 2014 IEEE
ISBN 9781479914883
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 4 times in Scopus Article | Citations
Altmetric details:
Access Statistics: 165 Abstract Views  -  Detailed Statistics
Created: Fri, 17 Apr 2015, 15:25:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us