Combining a Mixture of Experts with Transfer Learning in Complex Games

Mihai S. Dobre, Alex Lascarides

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present a supervised approach for learning policies in a highly complex game from small amounts of human data consisting of state–action pairs. Our Neural Network architecture can adapt to the varying size of the set of legal actions, thus bypassing the need to hardcode the actions in the output layer or iterate over them. This makes the training more data efficient. We use synthetic data created via game simulations among AI agents to show that a mixture of experts, where each expert predicts actions in different portions of the game, improves performance. We then show that this approach applied to human data also improves performance: in particular, using transfer learning to enable one expert to learn from another enhances performance on those portions of the game for which there is relatively little training data compared to other portions. The domain chosen for evaluation is the board game Settlers of Catan.
Original languageEnglish
Title of host publicationProceedings of the AAAI Spring Symposium: Learning from Observation of Humans
Place of PublicationStanford
PublisherAAAI Press
Pages487-493
Number of pages7
ISBN (Print)978-1-57735-779-7
Publication statusPublished - 20 Mar 2017
Event2017 AAAI Spring Symposium: Learning from Observation of Humans - Palo Alto, United States
Duration: 27 Mar 201729 Mar 2017
https://aaai.org/Library/Symposia/Spring/ss17-06.php

Conference

Conference2017 AAAI Spring Symposium: Learning from Observation of Humans
Abbreviated titleAAAI 2017
CountryUnited States
CityPalo Alto
Period27/03/1729/03/17
Internet address

Fingerprint

Dive into the research topics of 'Combining a Mixture of Experts with Transfer Learning in Complex Games'. Together they form a unique fingerprint.

Cite this