PackIt: A Virtual Environment for Geometric Planning

Ankit Goyal, Jia Deng
Proceedings of the 37th International Conference on Machine Learning, PMLR 119:3700-3710, 2020.

Abstract

The ability to jointly understand the geometry of objects and plan actions for manipulating them is crucial for intelligent agents. We refer to this ability as geometric planning. Recently, many interactive environments have been proposed to evaluate intelligent agents on various skills, however, none of them cater to the needs of geometric planning. We present PackIt, a virtual environment to evaluate and potentially learn the ability to do geometric planning, where an agent needs to take a sequence of actions to pack a set of objects into a box with limited space. We also construct a set of challenging packing tasks using an evolutionary algorithm. Further, we study various baselines for the task that include model-free learning-based and heuristic-based methods, as well as search-based optimization methods that assume access to the model of the environment.

Cite this Paper


BibTeX
@InProceedings{pmlr-v119-goyal20b, title = {{P}ack{I}t: A Virtual Environment for Geometric Planning}, author = {Goyal, Ankit and Deng, Jia}, booktitle = {Proceedings of the 37th International Conference on Machine Learning}, pages = {3700--3710}, year = {2020}, editor = {III, Hal Daumé and Singh, Aarti}, volume = {119}, series = {Proceedings of Machine Learning Research}, month = {13--18 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v119/goyal20b/goyal20b.pdf}, url = {http://proceedings.mlr.press/v119/goyal20b.html}, abstract = {The ability to jointly understand the geometry of objects and plan actions for manipulating them is crucial for intelligent agents. We refer to this ability as geometric planning. Recently, many interactive environments have been proposed to evaluate intelligent agents on various skills, however, none of them cater to the needs of geometric planning. We present PackIt, a virtual environment to evaluate and potentially learn the ability to do geometric planning, where an agent needs to take a sequence of actions to pack a set of objects into a box with limited space. We also construct a set of challenging packing tasks using an evolutionary algorithm. Further, we study various baselines for the task that include model-free learning-based and heuristic-based methods, as well as search-based optimization methods that assume access to the model of the environment.} }
Endnote
%0 Conference Paper %T PackIt: A Virtual Environment for Geometric Planning %A Ankit Goyal %A Jia Deng %B Proceedings of the 37th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2020 %E Hal Daumé III %E Aarti Singh %F pmlr-v119-goyal20b %I PMLR %P 3700--3710 %U http://proceedings.mlr.press/v119/goyal20b.html %V 119 %X The ability to jointly understand the geometry of objects and plan actions for manipulating them is crucial for intelligent agents. We refer to this ability as geometric planning. Recently, many interactive environments have been proposed to evaluate intelligent agents on various skills, however, none of them cater to the needs of geometric planning. We present PackIt, a virtual environment to evaluate and potentially learn the ability to do geometric planning, where an agent needs to take a sequence of actions to pack a set of objects into a box with limited space. We also construct a set of challenging packing tasks using an evolutionary algorithm. Further, we study various baselines for the task that include model-free learning-based and heuristic-based methods, as well as search-based optimization methods that assume access to the model of the environment.
APA
Goyal, A. & Deng, J.. (2020). PackIt: A Virtual Environment for Geometric Planning. Proceedings of the 37th International Conference on Machine Learning, in Proceedings of Machine Learning Research 119:3700-3710 Available from http://proceedings.mlr.press/v119/goyal20b.html.

Related Material