Deep Bayesian Nonparametric Learning of Rules and Plans from Demonstrations with a Learned Automaton Prior
<jats:p>We introduce a method to learn imitative 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 integr...
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Association for the Advancement of Artificial Intelligence (AAAI)
2021
|
| Online Access: | https://hdl.handle.net/1721.1/135230 |
| _version_ | 1811097872661217280 |
|---|---|
| author | Araki, Brandon Vodrahalli, Kiran Leech, Thomas Vasile, Cristian-Ioan Donahue, Mark Rus, Daniela |
| author2 | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science |
| author_facet | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Araki, Brandon Vodrahalli, Kiran Leech, Thomas Vasile, Cristian-Ioan Donahue, Mark Rus, Daniela |
| author_sort | Araki, Brandon |
| collection | MIT |
| description | <jats:p>We introduce a method to learn imitative 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, 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. We build upon previous work by no longer requiring additional supervised information which is hard to collect in practice. We achieve this by using a deep Bayesian nonparametric hierarchical model. We test our model on several domains and also show results for a real-world implementation on a mobile robotic arm platform.</jats:p> |
| first_indexed | 2024-09-23T17:06:18Z |
| format | Article |
| id | mit-1721.1/135230 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T17:06:18Z |
| publishDate | 2021 |
| publisher | Association for the Advancement of Artificial Intelligence (AAAI) |
| record_format | dspace |
| spelling | mit-1721.1/1352302023-01-20T20:33:02Z Deep Bayesian Nonparametric Learning of Rules and Plans from Demonstrations with a Learned Automaton Prior Araki, Brandon Vodrahalli, Kiran Leech, Thomas Vasile, Cristian-Ioan Donahue, Mark Rus, Daniela Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Lincoln Laboratory <jats:p>We introduce a method to learn imitative 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, 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. We build upon previous work by no longer requiring additional supervised information which is hard to collect in practice. We achieve this by using a deep Bayesian nonparametric hierarchical model. We test our model on several domains and also show results for a real-world implementation on a mobile robotic arm platform.</jats:p> 2021-10-27T20:22:34Z 2021-10-27T20:22:34Z 2020 2021-04-12T14:38:37Z Article http://purl.org/eprint/type/ConferencePaper https://hdl.handle.net/1721.1/135230 en 10.1609/AAAI.V34I06.6559 Proceedings of the AAAI Conference on Artificial Intelligence Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Association for the Advancement of Artificial Intelligence (AAAI) Other repository |
| spellingShingle | Araki, Brandon Vodrahalli, Kiran Leech, Thomas Vasile, Cristian-Ioan Donahue, Mark Rus, Daniela Deep Bayesian Nonparametric Learning of Rules and Plans from Demonstrations with a Learned Automaton Prior |
| title | Deep Bayesian Nonparametric Learning of Rules and Plans from Demonstrations with a Learned Automaton Prior |
| title_full | Deep Bayesian Nonparametric Learning of Rules and Plans from Demonstrations with a Learned Automaton Prior |
| title_fullStr | Deep Bayesian Nonparametric Learning of Rules and Plans from Demonstrations with a Learned Automaton Prior |
| title_full_unstemmed | Deep Bayesian Nonparametric Learning of Rules and Plans from Demonstrations with a Learned Automaton Prior |
| title_short | Deep Bayesian Nonparametric Learning of Rules and Plans from Demonstrations with a Learned Automaton Prior |
| title_sort | deep bayesian nonparametric learning of rules and plans from demonstrations with a learned automaton prior |
| url | https://hdl.handle.net/1721.1/135230 |
| work_keys_str_mv | AT arakibrandon deepbayesiannonparametriclearningofrulesandplansfromdemonstrationswithalearnedautomatonprior AT vodrahallikiran deepbayesiannonparametriclearningofrulesandplansfromdemonstrationswithalearnedautomatonprior AT leechthomas deepbayesiannonparametriclearningofrulesandplansfromdemonstrationswithalearnedautomatonprior AT vasilecristianioan deepbayesiannonparametriclearningofrulesandplansfromdemonstrationswithalearnedautomatonprior AT donahuemark deepbayesiannonparametriclearningofrulesandplansfromdemonstrationswithalearnedautomatonprior AT rusdaniela deepbayesiannonparametriclearningofrulesandplansfromdemonstrationswithalearnedautomatonprior |