{"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/reinforcement-learning-for-pivoting-task","title":"Reinforcement Learning for Pivoting Task","arxiv_id":"1703.00472","date":"2017-03-01","proceeding":null,"authors":["Rika Antonova","Silvia Cruciani","Christian Smith","Danica Kragic"],"abstract":"In this work we propose an approach to learn a robust policy for solving the\npivoting task. Recently, several model-free continuous control algorithms were\nshown to learn successful policies without prior knowledge of the dynamics of\nthe task. However, obtaining successful policies required thousands to millions\nof training episodes, limiting the applicability of these approaches to real\nhardware. We developed a training procedure that allows us to use a simple\ncustom simulator to learn policies robust to the mismatch of simulation vs\nrobot. In our experiments, we demonstrate that the policy learned in the\nsimulator is able to pivot the object to the desired target angle on the real\nrobot. We also show generalization to an object with different inertia, shape,\nmass and friction properties than those used during training. This result is a\nstep towards making model-free reinforcement learning available for solving\nrobotics tasks via pre-training in simulators that offer only an imprecise\nmatch to the real-world dynamics.","url_abs":"http://arxiv.org/abs/1703.00472v1","url_pdf":"http://arxiv.org/pdf/1703.00472v1.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":"reinforcement-learning-for-pivoting-task","repo_url":"https://github.com/LeoToledo/PivotingTaskRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"continuous-control","task_name":"Continuous Control"},{"task_slug":"friction","task_name":"Friction"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"continuous-control","task_name":"continuous-control"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1703.00472","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}