{"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/humanoid-gym-reinforcement-learning-for","title":"Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer","arxiv_id":"2404.05695","date":"2024-04-08","proceeding":null,"authors":["Xinyang Gu","Yen-Jen Wang","Jianyu Chen"],"abstract":"Humanoid-Gym is an easy-to-use reinforcement learning (RL) framework based on Nvidia Isaac Gym, designed to train locomotion skills for humanoid robots, emphasizing zero-shot transfer from simulation to the real-world environment. Humanoid-Gym also integrates a sim-to-sim framework from Isaac Gym to Mujoco that allows users to verify the trained policies in different physical simulations to ensure the robustness and generalization of the policies. This framework is verified by RobotEra's XBot-S (1.2-meter tall humanoid robot) and XBot-L (1.65-meter tall humanoid robot) in a real-world environment with zero-shot sim-to-real transfer. The project website and source code can be found at: https://sites.google.com/view/humanoid-gym/.","url_abs":"https://arxiv.org/abs/2404.05695v2","url_pdf":"https://arxiv.org/pdf/2404.05695v2.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":"humanoid-gym-reinforcement-learning-for","repo_url":"https://github.com/roboterax/humanoid-gym","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"mujoco","task_name":"MuJoCo"},{"task_slug":"physical-simulations","task_name":"Physical Simulations"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.05695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05695"}},"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/roboterax/humanoid-gym","reach":null}],"summary":{"ran_draft_wrong":1,"ran_honours":1,"ran_violates":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"a1fbd4bf78365ac9","entry":"get_obs","repo":"roboterax/humanoid-gym","repo_kind":"official","path":"humanoid/scripts/sim2sim.py","file_url":"https://github.com/roboterax/humanoid-gym/blob/HEAD/humanoid/scripts/sim2sim.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a1fbd4bf78365ac9"}},{"code_sha256_prefix":"f17dba32a52f00bd","entry":"pd_control","repo":"roboterax/humanoid-gym","repo_kind":"official","path":"humanoid/scripts/sim2sim.py","file_url":"https://github.com/roboterax/humanoid-gym/blob/HEAD/humanoid/scripts/sim2sim.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f17dba32a52f00bd"}},{"code_sha256_prefix":"7daa9646f1645a48","entry":"quaternion_to_euler_array","repo":"roboterax/humanoid-gym","repo_kind":"official","path":"humanoid/scripts/sim2sim.py","file_url":"https://github.com/roboterax/humanoid-gym/blob/HEAD/humanoid/scripts/sim2sim.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7daa9646f1645a48"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}