Learning and planning with logical automata
Name
10514_2021_Article_9993.pdf
Size
2.59 MB
Format
Adobe PDF
Checksum (MD5)
09481dc06b9076e9c9f44f8d2a964a82
Author(s)
Araki, Brandon
Vodrahalli, Kiran
Leech, Thomas
Vasile, Cristian-Ioan
Donahue, Mark
Rus, Daniela
Date Issued
August 13, 2021
Publisher
Springer US
Citation
Araki, Brandon, Vodrahalli, Kiran, Leech, Thomas, Vasile, Cristian-Ioan, Donahue, Mark et al. 2021. "Learning and planning with logical automata."
Version
Final published version
Abstract
Abstract
We introduce a method to learn policies from expert demonstrations that are interpretable and manipulable. We achieve interpretability by modeling the interactions between high-level actions as an automaton with connections to formal logic. We achieve manipulability by integrating this automaton into planning via Logical Value Iteration, so that changes to the automaton have predictable effects on the learned behavior. These qualities allow a human user to first understand what the model has learned, and then either correct the learned behavior or zero-shot generalize to new, similar tasks. Our inference method requires only low-level trajectories and a description of the environment in order to learn high-level rules. We achieve this by using a deep Bayesian nonparametric hierarchical model. We test our model on several domains of interest and also show results for a real-world implementation on a mobile robotic arm platform for lunchbox-packing and cabinet-opening tasks.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Lincoln Laboratory
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1007/s10514-021-09993-6
