Few-Shot Bayesian Imitation Learning with Logical Program Policies
Name
6587-Article Text-9812-1-10-20200520.pdf
Description
Published version
Size
2.87 MB
Format
Adobe PDF
Checksum (MD5)
badbd3f7efdc0eeab9a82f5c054e8a9e
Author(s)
Silver, Tom
Allen, Kelsey R
Lew, Alex K
Pack Kaelbling, Leslie
Tenenbaum, Josh
Date Issued
2020
Journal
Proceedings of the AAAI Conference on Artificial Intelligence
Publisher
Association for the Advancement of Artificial Intelligence (AAAI)
Citation
Silver, Tom, Allen, Kelsey R, Lew, Alex K, Pack Kaelbling, Leslie and Tenenbaum, Josh. 2020. "Few-Shot Bayesian Imitation Learning with Logical Program Policies." Proceedings of the AAAI Conference on Artificial Intelligence, 34 (06).
Version
Final published version
Abstract
Humans can learn many novel tasks from a very small number (1–5) of demonstrations, in stark contrast to the data requirements of nearly tabula rasa deep learning methods. We propose an expressive class of policies, a strong but general prior, and a learning algorithm that, together, can learn interesting policies from very few examples. We represent policies as logical combinations of programs drawn from a domain-specific language (DSL), define a prior over policies with a probabilistic grammar, and derive an approximate Bayesian inference algorithm to learn policies from demonstrations. In experiments, we study six strategy games played on a 2D grid with one shared DSL. After a few demonstrations of each game, the inferred policies generalize to new game instances that differ substantially from the demonstrations. Our policy learning is 20–1,000x more data efficient than convolutional and fully convolutional policy learning and many orders of magnitude more computationally efficient than vanilla program induction. We argue that the proposed method is an apt choice for tasks that have scarce training data and feature significant, structured variation between task instances.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1609/AAAI.V34I06.6587
