Bayesian inference of temporal task specifications from demonstrations
Name
7637-bayesian-inference-of-temporal-task-specifications-from-demonstrations.pdf
Description
Published version
Size
6.28 MB
Format
Adobe PDF
Checksum (MD5)
7bd35340bf1f4540d06f0a7e2d58ac26
Author(s)
Shah, Ankit Jayesh
Kamath, Pritish
Li, Shen
Shah, Julie A
Date Issued
2018
Journal
Advances in Neural Information Processing Systems
Publisher
Neural Information Processing Systems Foundation, Inc.
Citation
Shah, Ankit, "Bayesian inference of temporal task specifications from demonstrations." Advances in Neural Information Processing Systems 31 (NIPS 2018), edited by S. Bengio, et al. (San Diego, Calif.: Neural Information Processing Systems Foundation, 2018): url https://papers.nips.cc/paper/7637-bayesian-inference-of-temporal-task-specifications-from-demonstrations
Version
Final published version
Abstract
When observing task demonstrations, human apprentices are able to identify whether a given task is executed correctly long before they gain expertise in actually performing that task. Prior research into learning from demonstrations (LfD) has failed to capture this notion of the acceptability of an execution; meanwhile, temporal logics provide a flexible language for expressing task specifications. Inspired by this, we present Bayesian specification inference, a probabilistic model for inferring task specification as a temporal logic formula. We incorporate methods from probabilistic programming to define our priors, along with a domain-independent likelihood function to enable sampling-based inference. We demonstrate the efficacy of our model for inferring specifications with over 90% similarity between the inferred specification and the ground truth, both within a synthetic domain and a real-world table setting task.
Description
Paper presented at the Annual Conference on Neural Information Processing Systems 2018 (NeurIPS 2018), 3-8 December 3-8, 2018, Montréal, Québec.
MIT Department
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://papers.nips.cc/paper/7637-bayesian-inference-of-temporal-task-specifications-from-demonstrations
