{"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-body-affordances-to-simplify-action","title":"Learning body-affordances to simplify action spaces","arxiv_id":"1708.04391","date":"2017-08-15","proceeding":null,"authors":["Nicholas Guttenberg","Martin Biehl","Ryota Kanai"],"abstract":"Controlling embodied agents with many actuated degrees of freedom is a\nchallenging task. We propose a method that can discover and interpolate between\ncontext dependent high-level actions or body-affordances. These provide an\nabstract, low-dimensional interface indexing high-dimensional and time-\nextended action policies. Our method is related to recent ap- proaches in the\nmachine learning literature but is conceptually simpler and easier to\nimplement. More specifically our method requires the choice of a n-dimensional\ntarget sensor space that is endowed with a distance metric. The method then\nlearns an also n-dimensional embedding of possibly reactive body-affordances\nthat spread as far as possible throughout the target sensor space.","url_abs":"http://arxiv.org/abs/1708.04391v1","url_pdf":"http://arxiv.org/pdf/1708.04391v1.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-body-affordances-to-simplify-action","repo_url":"https://github.com/arayabrain/AffordanceMapping","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}