{"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/deep-visual-foresight-for-planning-robot","title":"Deep Visual Foresight for Planning Robot Motion","arxiv_id":"1610.00696","date":"2016-10-03","proceeding":null,"authors":["Chelsea Finn","Sergey Levine"],"abstract":"A key challenge in scaling up robot learning to many skills and environments\nis removing the need for human supervision, so that robots can collect their\nown data and improve their own performance without being limited by the cost of\nrequesting human feedback. Model-based reinforcement learning holds the promise\nof enabling an agent to learn to predict the effects of its actions, which\ncould provide flexible predictive models for a wide range of tasks and\nenvironments, without detailed human supervision. We develop a method for\ncombining deep action-conditioned video prediction models with model-predictive\ncontrol that uses entirely unlabeled training data. Our approach does not\nrequire a calibrated camera, an instrumented training set-up, nor precise\nsensing and actuation. Our results show that our method enables a real robot to\nperform nonprehensile manipulation -- pushing objects -- and can handle novel\nobjects not seen during training.","url_abs":"http://arxiv.org/abs/1610.00696v2","url_pdf":"http://arxiv.org/pdf/1610.00696v2.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":"deep-visual-foresight-for-planning-robot","repo_url":"https://github.com/m-serra/action-inference-for-video-prediction-benchmarking","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"model-predictive-control","task_name":"Model Predictive Control"},{"task_slug":"model-based-reinforcement-learning","task_name":"Model-based Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"video-prediction","task_name":"Video Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1610.00696","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}