{"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/composable-action-conditioned-predictors","title":"Composable Action-Conditioned Predictors: Flexible Off-Policy Learning for Robot Navigation","arxiv_id":"1810.07167","date":"2018-10-16","proceeding":null,"authors":["Gregory Kahn","Adam Villaflor","Pieter Abbeel","Sergey Levine"],"abstract":"A general-purpose intelligent robot must be able to learn autonomously and be\nable to accomplish multiple tasks in order to be deployed in the real world.\nHowever, standard reinforcement learning approaches learn separate\ntask-specific policies and assume the reward function for each task is known a\npriori. We propose a framework that learns event cues from off-policy data, and\ncan flexibly combine these event cues at test time to accomplish different\ntasks. These event cue labels are not assumed to be known a priori, but are\ninstead labeled using learned models, such as computer vision detectors, and\nthen `backed up' in time using an action-conditioned predictive model. We show\nthat a simulated robotic car and a real-world RC car can gather data and train\nfully autonomously without any human-provided labels beyond those needed to\ntrain the detectors, and then at test-time be able to accomplish a variety of\ndifferent tasks. Videos of the experiments and code can be found at\nhttps://github.com/gkahn13/CAPs","url_abs":"http://arxiv.org/abs/1810.07167v1","url_pdf":"http://arxiv.org/pdf/1810.07167v1.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":"composable-action-conditioned-predictors","repo_url":"https://github.com/gkahn13/CAPs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"robot-navigation","task_name":"Robot Navigation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.07167","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}