UTCS Artificial Intelligence
courses
talks/events
demos
people
projects
publications
software/data
labs
areas
admin
Object-Model Transfer in the General Video Game Domain (2016)
Alexander Braylan,
Risto Miikkulainen
A transfer learning approach is presented to address the challenge of training video game agents with limited data. The approach decomposes games into objects, learns object models, and transfers models from known games to unfamiliar games to guide learning. Experiments show that the approach improves prediction accuracy over a comparable control, leading to more efficient exploration. Training of game agents is thus accelerated by transferring object models from previously learned games.
View:
PDF
Citation:
To Appear In
Proceedings of the Twelfth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment
2016.
Bibtex:
@inproceedings{braylan:aiide2016, title={Object-Model Transfer in the General Video Game Domain}, author={Alexander Braylan and Risto Miikkulainen}, booktitle={Proceedings of the Twelfth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment}, url="http://www.cs.utexas.edu/users/ai-lab?braylan:aiide16", year={2016} }
People
Risto Miikkulainen
Faculty
risto [at] cs utexas edu
Areas of Interest
Evolutionary Computation
Game Playing
General Game Playing
Learning for Planning and Problem Solving
Transfer Learning
Software/Data
Object Model Transfer JAVA
Code used for
Object-Model Transfer in the General Video Game Domain ...
2016
Labs
Neural Networks