{"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/deepmimic-example-guided-deep-reinforcement","title":"DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills","arxiv_id":"1804.02717","date":"2018-04-08","proceeding":null,"authors":["Xue Bin Peng","Pieter Abbeel","Sergey Levine","Michiel Van de Panne"],"abstract":"A longstanding goal in character animation is to combine data-driven\nspecification of behavior with a system that can execute a similar behavior in\na physical simulation, thus enabling realistic responses to perturbations and\nenvironmental variation. We show that well-known reinforcement learning (RL)\nmethods can be adapted to learn robust control policies capable of imitating a\nbroad range of example motion clips, while also learning complex recoveries,\nadapting to changes in morphology, and accomplishing user-specified goals. Our\nmethod handles keyframed motions, highly-dynamic actions such as\nmotion-captured flips and spins, and retargeted motions. By combining a\nmotion-imitation objective with a task objective, we can train characters that\nreact intelligently in interactive settings, e.g., by walking in a desired\ndirection or throwing a ball at a user-specified target. This approach thus\ncombines the convenience and motion quality of using motion clips to define the\ndesired style and appearance, with the flexibility and generality afforded by\nRL methods and physics-based animation. We further explore a number of methods\nfor integrating multiple clips into the learning process to develop\nmulti-skilled agents capable of performing a rich repertoire of diverse skills.\nWe demonstrate results using multiple characters (human, Atlas robot, bipedal\ndinosaur, dragon) and a large variety of skills, including locomotion,\nacrobatics, and martial arts.","url_abs":"http://arxiv.org/abs/1804.02717v3","url_pdf":"http://arxiv.org/pdf/1804.02717v3.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":"deepmimic-example-guided-deep-reinforcement","repo_url":"https://github.com/Sohojoe/ActiveRagdollStyleTransfer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"deepmimic-example-guided-deep-reinforcement","repo_url":"https://github.com/Unity-Technologies/marathon-envs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"deepmimic-example-guided-deep-reinforcement","repo_url":"https://github.com/kenfuliang/Awesome-Reinforcement-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"deepmimic-example-guided-deep-reinforcement","repo_url":"https://github.com/p-morais/gym-cassie","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"deepmimic-example-guided-deep-reinforcement","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"}},{"paper_slug":"deepmimic-example-guided-deep-reinforcement","repo_url":"https://github.com/xbpeng/DeepMimic","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"motion-synthesis","task_name":"Motion Synthesis"},{"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":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}