Learning Neuro-Symbolic Skills for Bilevel Planning

Tom Silver, Ashay Athalye, Joshua B. Tenenbaum, Tomás Lozano-Pérez, Leslie Pack Kaelbling
Proceedings of The 6th Conference on Robot Learning, PMLR 205:701-714, 2023.

Abstract

Decision-making is challenging in robotics environments with continuous object-centric states, continuous actions, long horizons, and sparse feedback. Hierarchical approaches, such as task and motion planning (TAMP), address these challenges by decomposing decision-making into two or more levels of abstraction. In a setting where demonstrations and symbolic predicates are given, prior work has shown how to learn symbolic operators and neural samplers for TAMP with manually designed parameterized policies. Our main contribution is a method for learning parameterized polices in combination with operators and samplers. These components are packaged into modular neuro-symbolic skills and sequenced together with search-then-sample TAMP to solve new tasks. In experiments in four robotics domains, we show that our approach — bilevel planning with neuro-symbolic skills — can solve a wide range of tasks with varying initial states, goals, and objects, outperforming six baselines and ablations.

Cite this Paper

BibTeX
@InProceedings{pmlr-v205-silver23a, title = {Learning Neuro-Symbolic Skills for Bilevel Planning}, author = {Silver, Tom and Athalye, Ashay and Tenenbaum, Joshua B. and Lozano-P\'erez, Tom\'as and Kaelbling, Leslie Pack}, booktitle = {Proceedings of The 6th Conference on Robot Learning}, pages = {701--714}, year = {2023}, editor = {Liu, Karen and Kulic, Dana and Ichnowski, Jeff}, volume = {205}, series = {Proceedings of Machine Learning Research}, month = {14--18 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v205/silver23a/silver23a.pdf}, url = {https://proceedings.mlr.press/v205/silver23a.html}, abstract = {Decision-making is challenging in robotics environments with continuous object-centric states, continuous actions, long horizons, and sparse feedback. Hierarchical approaches, such as task and motion planning (TAMP), address these challenges by decomposing decision-making into two or more levels of abstraction. In a setting where demonstrations and symbolic predicates are given, prior work has shown how to learn symbolic operators and neural samplers for TAMP with manually designed parameterized policies. Our main contribution is a method for learning parameterized polices in combination with operators and samplers. These components are packaged into modular neuro-symbolic skills and sequenced together with search-then-sample TAMP to solve new tasks. In experiments in four robotics domains, we show that our approach — bilevel planning with neuro-symbolic skills — can solve a wide range of tasks with varying initial states, goals, and objects, outperforming six baselines and ablations.} }
Endnote
%0 Conference Paper %T Learning Neuro-Symbolic Skills for Bilevel Planning %A Tom Silver %A Ashay Athalye %A Joshua B. Tenenbaum %A Tomás Lozano-Pérez %A Leslie Pack Kaelbling %B Proceedings of The 6th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2023 %E Karen Liu %E Dana Kulic %E Jeff Ichnowski %F pmlr-v205-silver23a %I PMLR %P 701--714 %U https://proceedings.mlr.press/v205/silver23a.html %V 205 %X Decision-making is challenging in robotics environments with continuous object-centric states, continuous actions, long horizons, and sparse feedback. Hierarchical approaches, such as task and motion planning (TAMP), address these challenges by decomposing decision-making into two or more levels of abstraction. In a setting where demonstrations and symbolic predicates are given, prior work has shown how to learn symbolic operators and neural samplers for TAMP with manually designed parameterized policies. Our main contribution is a method for learning parameterized polices in combination with operators and samplers. These components are packaged into modular neuro-symbolic skills and sequenced together with search-then-sample TAMP to solve new tasks. In experiments in four robotics domains, we show that our approach — bilevel planning with neuro-symbolic skills — can solve a wide range of tasks with varying initial states, goals, and objects, outperforming six baselines and ablations.
APA
Silver, T., Athalye, A., Tenenbaum, J.B., Lozano-Pérez, T. & Kaelbling, L.P.. (2023). Learning Neuro-Symbolic Skills for Bilevel Planning. Proceedings of The 6th Conference on Robot Learning, in Proceedings of Machine Learning Research 205:701-714 Available from https://proceedings.mlr.press/v205/silver23a.html.

Related Material