Bayesian inference of temporal task specifications from demonstrations
Paper presented at the Annual Conference on Neural Information Processing Systems 2018 (NeurIPS 2018), 3-8 December 3-8, 2018, Montréal, Québec.
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Neural Information Processing Systems Foundation, Inc.
2020
|
| Online Access: | https://hdl.handle.net/1721.1/125873 |
| _version_ | 1826212573687578624 |
|---|---|
| author | Shah, Ankit Jayesh Kamath, Pritish Li, Shen Shah, Julie A |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Shah, Ankit Jayesh Kamath, Pritish Li, Shen Shah, Julie A |
| author_sort | Shah, Ankit Jayesh |
| collection | MIT |
| description | Paper presented at the Annual Conference on Neural Information Processing Systems 2018 (NeurIPS 2018), 3-8 December 3-8, 2018, Montréal, Québec. |
| first_indexed | 2024-09-23T15:25:43Z |
| format | Article |
| id | mit-1721.1/125873 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T15:25:43Z |
| publishDate | 2020 |
| publisher | Neural Information Processing Systems Foundation, Inc. |
| record_format | dspace |
| spelling | mit-1721.1/1258732022-10-02T02:41:31Z Bayesian inference of temporal task specifications from demonstrations Shah, Ankit Jayesh Kamath, Pritish Li, Shen Shah, Julie A Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Paper presented at the Annual Conference on Neural Information Processing Systems 2018 (NeurIPS 2018), 3-8 December 3-8, 2018, Montréal, Québec. 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. 2020-06-18T21:20:33Z 2020-06-18T21:20:33Z 2018 2019-10-31T18:34:23Z Article http://purl.org/eprint/type/ConferencePaper https://hdl.handle.net/1721.1/125873 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 en https://papers.nips.cc/paper/7637-bayesian-inference-of-temporal-task-specifications-from-demonstrations Advances in Neural Information Processing Systems 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. application/pdf Neural Information Processing Systems Foundation, Inc. Neural Information Processing Systems (NIPS) |
| spellingShingle | Shah, Ankit Jayesh Kamath, Pritish Li, Shen Shah, Julie A Bayesian inference of temporal task specifications from demonstrations |
| title | Bayesian inference of temporal task specifications from demonstrations |
| title_full | Bayesian inference of temporal task specifications from demonstrations |
| title_fullStr | Bayesian inference of temporal task specifications from demonstrations |
| title_full_unstemmed | Bayesian inference of temporal task specifications from demonstrations |
| title_short | Bayesian inference of temporal task specifications from demonstrations |
| title_sort | bayesian inference of temporal task specifications from demonstrations |
| url | https://hdl.handle.net/1721.1/125873 |
| work_keys_str_mv | AT shahankitjayesh bayesianinferenceoftemporaltaskspecificationsfromdemonstrations AT kamathpritish bayesianinferenceoftemporaltaskspecificationsfromdemonstrations AT lishen bayesianinferenceoftemporaltaskspecificationsfromdemonstrations AT shahjuliea bayesianinferenceoftemporaltaskspecificationsfromdemonstrations |