UTCS Artificial Intelligence
courses
talks/events
demos
people
projects
publications
software/data
labs
areas
admin
Reuse of Neural Modules for General Video Game Playing (2016)
Alexander Braylan, Mark Hollenbeck,
Elliot Meyerson
and
Risto Miikkulainen
A general approach to knowledge transfer is introduced in which an agent controlled by a neural network adapts how it reuses existing networks as it learns in a new domain. Networks trained for a new domain can improve their performance by routing activation selectively through previously learned neural structure, regardless of how or for what it was learned. A neuroevolution implementation of this approach is presented with application to high-dimensional sequential decision-making domains. This approach is more general than previous approaches to neural transfer for reinforcement learning. It is domain-agnostic and requires no prior assumptions about the nature of task relatedness or mappings. The method is analyzed in a stochastic version of the Arcade Learning Environment, demonstrating that it improves performance in some of the more complex Atari 2600 games, and that the success of transfer can be predicted based on a high-level characterization of game dynamics.
View:
PDF
Citation:
To Appear In
Proceedings of the 30th AAAI Conference on Artificial Intelligence (AAAI-16)
2016.
Bibtex:
@inproceedings{braylan:aaai16, title={Reuse of Neural Modules for General Video Game Playing}, author={Alexander Braylan and Mark Hollenbeck and Elliot Meyerson and Risto Miikkulainen}, booktitle={Proceedings of the 30th AAAI Conference on Artificial Intelligence (AAAI-16)}, url="http://www.cs.utexas.edu/users/ai-lab?braylan:aaai16", year={2016} }
People
Elliot Meyerson
Ph.D. Alumni
ekm [at] cs utexas edu
Risto Miikkulainen
Faculty
risto [at] cs utexas edu
Areas of Interest
Cognitive Science
Control
Evolutionary Computation
Game Playing
Neuroevolution
Labs
Neural Networks