{"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/learning-agile-and-dynamic-motor-skills-for","title":"Learning agile and dynamic motor skills for legged robots","arxiv_id":"1901.08652","date":"2019-01-24","proceeding":null,"authors":["Jemin Hwangbo","JoonHo Lee","Alexey Dosovitskiy","Dario Bellicoso","Vassilios Tsounis","Vladlen Koltun","Marco Hutter"],"abstract":"Legged robots pose one of the greatest challenges in robotics. Dynamic and\nagile maneuvers of animals cannot be imitated by existing methods that are\ncrafted by humans. A compelling alternative is reinforcement learning, which\nrequires minimal craftsmanship and promotes the natural evolution of a control\npolicy. However, so far, reinforcement learning research for legged robots is\nmainly limited to simulation, and only few and comparably simple examples have\nbeen deployed on real systems. The primary reason is that training with real\nrobots, particularly with dynamically balancing systems, is complicated and\nexpensive. In the present work, we introduce a method for training a neural\nnetwork policy in simulation and transferring it to a state-of-the-art legged\nsystem, thereby leveraging fast, automated, and cost-effective data generation\nschemes. The approach is applied to the ANYmal robot, a sophisticated\nmedium-dog-sized quadrupedal system. Using policies trained in simulation, the\nquadrupedal machine achieves locomotion skills that go beyond what had been\nachieved with prior methods: ANYmal is capable of precisely and\nenergy-efficiently following high-level body velocity commands, running faster\nthan before, and recovering from falling even in complex configurations.","url_abs":"http://arxiv.org/abs/1901.08652v1","url_pdf":"http://arxiv.org/pdf/1901.08652v1.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":"learning-agile-and-dynamic-motor-skills-for","repo_url":"https://github.com/junja94/anymal_science_robotics_supplementary","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"learning-agile-and-dynamic-motor-skills-for","repo_url":"https://github.com/awesomericky/complex-env-navigation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"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":"https://app.syntology.ai/?focus=1901.08652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.08652"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/junja94/anymal_science_robotics_supplementary","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/awesomericky/complex-env-navigation","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":1},"by_repo_kind":{"listed":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"7993a9cba13615a9","entry":"make_batch_all","repo":"awesomericky/complex-env-navigation","repo_kind":"listed","path":"raisimGymTorch/env/envs/train/trainer.py","file_url":"https://github.com/awesomericky/complex-env-navigation/blob/HEAD/raisimGymTorch/env/envs/train/trainer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7993a9cba13615a9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}