Projects per year
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 language | English |
---|---|
Title of host publication | Proceedings of the AAAI Spring Symposium: Learning from Observation of Humans |
Place of Publication | Stanford |
Publisher | AAAI Press |
Pages | 487-493 |
Number of pages | 7 |
ISBN (Print) | 978-1-57735-779-7 |
Publication status | Published - 20 Mar 2017 |
Event | 2017 AAAI Spring Symposium: Learning from Observation of Humans - Palo Alto, United States Duration: 27 Mar 2017 → 29 Mar 2017 https://aaai.org/Library/Symposia/Spring/ss17-06.php |
Conference
Conference | 2017 AAAI Spring Symposium: Learning from Observation of Humans |
---|---|
Abbreviated title | AAAI 2017 |
Country/Territory | United States |
City | Palo Alto |
Period | 27/03/17 → 29/03/17 |
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.Projects
- 1 Finished