Reusing skills for first-time solution of navigation tasks in platform videogames

Dann, M, Zambetta, F and Thangarajah, J 2017, 'Reusing skills for first-time solution of navigation tasks in platform videogames', in Proceedings of the 16th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2017), Sao Paulo, Brasil, 8-12 May 2017, pp. 1517-1519.


Document type: Conference Paper
Collection: Conference Papers

Attached Files
Name Description MIMEType Size
n2006075493.pdf Published Version application/pdf 845.72KB
Title Reusing skills for first-time solution of navigation tasks in platform videogames
Author(s) Dann, M
Zambetta, F
Thangarajah, J
Year 2017
Conference name AAMAS 2017
Conference location Sao Paulo, Brasil
Conference dates 8-12 May 2017
Proceedings title Proceedings of the 16th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2017)
Publisher International Foundation for Autonomous Agents and Multiagent Systems
Place of publication Sao Paulo, Brasil
Start page 1517
End page 1519
Total pages 3
Abstract We consider the problem of performing real-time navigation in domains where a "god's eye view"is provided. One setting where this challenge arises is in platform videogames, occurring whenever the player wishes to reach an item or powerup on the current screen. Previous agents for these games rely on generating many low-level simulations or training runs for each fixed task. Human players, on the other hand, can solve navigation tasks at a high level by visualising sequences of abstract "skills". Based on this intuition, we introduce a novel planning approach and apply it to Infinite Mario. Despite facing randomly generated, maze-like tasks, our agent is capable of deriving complex plans in real-time, without exploiting precise knowledge of the game's code.
Subjects Adaptive Agents and Intelligent Robotics
Virtual Reality and Related Simulation
Keyword(s) Reinforcement Learning
Videogames
Options Framework
Copyright notice © 2017, International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org). All rights reserved.
Versions
Version Filter Type
Access Statistics: 133 Abstract Views, 50 File Downloads  -  Detailed Statistics
Created: Wed, 26 Jul 2017, 07:56:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us