Object-Model Transfer in the General Video Game Domain
DOI:
https://doi.org/10.1609/aiide.v12i1.12870Keywords:
Transfer Learning, General Video Game PlayingAbstract
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.
Downloads
Published
2021-06-25
How to Cite
Braylan, A., & Miikkulainen, R. (2021). Object-Model Transfer in the General Video Game Domain. Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 12(1), 136-142. https://doi.org/10.1609/aiide.v12i1.12870
Issue
Section
Poster Papers