{"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-and-imitation-learning-for","title":"Reinforcement and Imitation Learning for Diverse Visuomotor Skills","arxiv_id":"1802.09564","date":"2018-02-26","proceeding":"ICLR 2018 1","authors":["Yuke Zhu","Ziyu Wang","Josh Merel","Andrei Rusu","Tom Erez","Serkan Cabi","Saran Tunyasuvunakool","János Kramár","Raia Hadsell","Nando de Freitas","Nicolas Heess"],"abstract":"We propose a model-free deep reinforcement learning method that leverages a\nsmall amount of demonstration data to assist a reinforcement learning agent. We\napply this approach to robotic manipulation tasks and train end-to-end\nvisuomotor policies that map directly from RGB camera inputs to joint\nvelocities. We demonstrate that our approach can solve a wide variety of\nvisuomotor tasks, for which engineering a scripted controller would be\nlaborious. In experiments, our reinforcement and imitation agent achieves\nsignificantly better performances than agents trained with reinforcement\nlearning or imitation learning alone. We also illustrate that these policies,\ntrained with large visual and dynamics variations, can achieve preliminary\nsuccesses in zero-shot sim2real transfer. A brief visual description of this\nwork can be viewed in https://youtu.be/EDl8SQUNjj0","url_abs":"http://arxiv.org/abs/1802.09564v2","url_pdf":"http://arxiv.org/pdf/1802.09564v2.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-and-imitation-learning-for","repo_url":"https://github.com/pairlab/robosuite","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"imitation-learning","task_name":"Imitation Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1802.09564","atlas_url":"https://app.syntology.ai/?focus=1802.09564","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}