{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/sfv-reinforcement-learning-of-physical-skills","title":"SFV: Reinforcement Learning of Physical Skills from Videos","arxiv_id":"1810.03599","date":"2018-10-08","proceeding":null,"authors":["Xue Bin Peng","Angjoo Kanazawa","Jitendra Malik","Pieter Abbeel","Sergey Levine"],"abstract":"Data-driven character animation based on motion capture can produce highly\nnaturalistic behaviors and, when combined with physics simulation, can provide\nfor natural procedural responses to physical perturbations, environmental\nchanges, and morphological discrepancies. Motion capture remains the most\npopular source of motion data, but collecting mocap data typically requires\nheavily instrumented environments and actors. In this paper, we propose a\nmethod that enables physically simulated characters to learn skills from videos\n(SFV). Our approach, based on deep pose estimation and deep reinforcement\nlearning, allows data-driven animation to leverage the abundance of publicly\navailable video clips from the web, such as those from YouTube. This has the\npotential to enable fast and easy design of character controllers simply by\nquerying for video recordings of the desired behavior. The resulting\ncontrollers are robust to perturbations, can be adapted to new settings, can\nperform basic object interactions, and can be retargeted to new morphologies\nvia reinforcement learning. We further demonstrate that our method can predict\npotential human motions from still images, by forward simulation of learned\ncontrollers initialized from the observed pose. Our framework is able to learn\na broad range of dynamic skills, including locomotion, acrobatics, and martial\narts.","url_abs":"http://arxiv.org/abs/1810.03599v2","url_pdf":"http://arxiv.org/pdf/1810.03599v2.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":"sfv-reinforcement-learning-of-physical-skills","repo_url":"https://github.com/akanazawa/motion_reconstruction","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":"pose-estimation","task_name":"Pose Estimation"},{"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":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"akanazawa/motion_reconstruction","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"1dee6750960ff7ecfdd1c05714c573e9bad308d36ad9bf8549bfd1f5b06b8e72","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}