Bayesian Inference of Linear Temporal Logic Specifications for Contrastive Explanations
Name
kim-IJCAI-2019-preprint.pdf
Description
Accepted version
Size
791.58 KB
Format
Adobe PDF
Checksum (MD5)
0e31c93c95f3bfd5b70b0537d6252d20
Author(s)
Kim, Joseph
Muise, Christian
Shah, Ankit Jayesh
Agarwal, Shubham
Shah, Julie A
Date Issued
2019
Journal
IJCAI International Joint Conference on Artificial Intelligence
Publisher
International Joint Conferences on Artificial Intelligence
Citation
Kim, Joseph, Muise, Christian, Shah, Ankit Jayesh, Agarwal, Shubham and Shah, Julie A. 2019. "Bayesian Inference of Linear Temporal Logic Specifications for Contrastive Explanations." IJCAI International Joint Conference on Artificial Intelligence, 2019-August.
Version
Author's final manuscript
Abstract
© 2019 International Joint Conferences on Artificial Intelligence. All rights reserved. Temporal logics are useful for providing concise descriptions of system behavior, and have been successfully used as a language for goal definitions in task planning. Prior works on inferring temporal logic specifications have focused on “summarizing” the input dataset - i.e., finding specifications that are satisfied by all plan traces belonging to the given set. In this paper, we examine the problem of inferring specifications that describe temporal differences between two sets of plan traces. We formalize the concept of providing such contrastive explanations, then present BayesLTL - a Bayesian probabilistic model for inferring contrastive explanations as linear temporal logic (LTL) specifications. We demonstrate the robustness and scalability of our model for inferring accurate specifications from noisy data and across various benchmark planning domains.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
MIT-IBM Watson AI Lab
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.24963/IJCAI.2019/776
