{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/learning-quickly-to-plan-quickly-using","title":"Learning Quickly to Plan Quickly Using Modular Meta-Learning","arxiv_id":"1809.07878","date":"2018-09-20","proceeding":null,"authors":["Rohan Chitnis","Leslie Pack Kaelbling","Tomás Lozano-Pérez"],"abstract":"Multi-object manipulation problems in continuous state and action spaces can\nbe solved by planners that search over sampled values for the continuous\nparameters of operators. The efficiency of these planners depends critically on\nthe effectiveness of the samplers used, but effective sampling in turn depends\non details of the robot, environment, and task. Our strategy is to learn\nfunctions called \"specializers\" that generate values for continuous operator\nparameters, given a state description and values for the discrete parameters.\nRather than trying to learn a single specializer for each operator from large\namounts of data on a single task, we take a modular meta-learning approach. We\ntrain on multiple tasks and learn a variety of specializers that, on a new\ntask, can be quickly adapted using relatively little data -- thus, our system\n\"learns quickly to plan quickly\" using these specializers. We validate our\napproach experimentally in simulated 3D pick-and-place tasks with continuous\nstate and action spaces. Visit http://tinyurl.com/chitnis-icra-19 for a\nsupplementary video.","url_abs":"http://arxiv.org/abs/1809.07878v2","url_pdf":"http://arxiv.org/pdf/1809.07878v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"learning-quickly-to-plan-quickly-using","repo_url":"https://github.com/FerranAlet/modular-metalearning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"meta-learning","task_name":"Meta-Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.07878","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}