{"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":"/task/humanoid-control","name":"Humanoid Control","slug":"humanoid-control","description_markdown":"Control of a high-dimensional humanoid. This can include skill learning by tracking motion capture clips, learning goal-directed tasks like going towards a moving target, and generating motion within a physics simulator.","categories":[{"name":"Robots","url":"/area/robots"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":37,"papers_with_code":12,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":0,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":37,"of":37,"of_with_code":12,"tagged_in_all":37,"counts":{"archive_papers_tagged":37,"with_a_code_link":12,"where_syntology_ran_a_sample":4,"not_listed_spam_title":0,"listed":37,"listed_where_code_ran":4,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":4,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/zero-shot-whole-body-humanoid-control-via","slug":"zero-shot-whole-body-humanoid-control-via","title":"Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models","date":"2025-04-15","arxiv_id":"2504.11054","repositories_listed":2,"syntology":{"n":31,"n_ran":16,"n_constructed":9,"n_ran_checked":10,"n_instrument":6,"n_unverified":15,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":31,"phrase":"16 ran (of which 9 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 6 where Syntology's instrument failed) · 15 unverified","sample_list":"/paper/zero-shot-whole-body-humanoid-control-via#ran","syntology_url":"https://syntology.ai/paper/2504.11054","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.11054"}},"official":{"repos":["facebookresearch/humenv","facebookresearch/metamotivo"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":9,"n_ran_no_instrument_failure":10,"n_unverified":15,"ran_from_kinds":["official"]}}},{"url":"/paper/skillblender-towards-versatile-humanoid-whole","slug":"skillblender-towards-versatile-humanoid-whole","title":"SkillBlender: Towards Versatile Humanoid Whole-Body Loco-Manipulation via Skill Blending","date":"2025-06-11","arxiv_id":"2506.09366","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-based-motion-imitation","slug":"reinforcement-learning-based-motion-imitation","title":"Reinforcement learning-based motion imitation for physiologically plausible musculoskeletal motor control","date":"2025-03-18","arxiv_id":"2503.14637","repositories_listed":1,"syntology":null},{"url":"/paper/2408-00342","slug":"2408-00342","title":"MuJoCo MPC for Humanoid Control: Evaluation on HumanoidBench","date":"2024-08-01","arxiv_id":"2408.00342","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/2408-00342#ran","syntology_url":"https://syntology.ai/paper/2408.00342","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.00342"}},"official":{"repos":["google-deepmind/mujoco_mpc"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mocapact-a-multi-task-dataset-for-simulated","slug":"mocapact-a-multi-task-dataset-for-simulated","title":"MoCapAct: A Multi-Task Dataset for Simulated Humanoid Control","date":"2022-08-15","arxiv_id":"2208.07363","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mocapact-a-multi-task-dataset-for-simulated#ran","syntology_url":"https://syntology.ai/paper/2208.07363","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.07363"}},"official":{"repos":["microsoft/MoCapAct"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-soccer-juggling-skills-with-layer","slug":"learning-soccer-juggling-skills-with-layer","title":"Learning Soccer Juggling Skills with Layer-wise Mixture-of-Experts","date":"2022-07-24","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/beyond-tabula-rasa-reincarnating","slug":"beyond-tabula-rasa-reincarnating","title":"Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress","date":"2022-06-03","arxiv_id":"2206.01626","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/beyond-tabula-rasa-reincarnating#ran","syntology_url":"https://syntology.ai/paper/2206.01626","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.01626"}},"official":{"repos":["google-research/reincarnating_rl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-brachiate-via-simplified-model","slug":"learning-to-brachiate-via-simplified-model","title":"Learning to Brachiate via Simplified Model Imitation","date":"2022-05-08","arxiv_id":"2205.03943","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-model-based-stochastic-value-gradient","slug":"on-the-model-based-stochastic-value-gradient","title":"On the model-based stochastic value gradient for continuous reinforcement learning","date":"2020-08-28","arxiv_id":"2008.12775","repositories_listed":1,"syntology":null},{"url":"/paper/clipup-a-simple-and-powerful-optimizer-for","slug":"clipup-a-simple-and-powerful-optimizer-for","title":"ClipUp: A Simple and Powerful Optimizer for Distribution-based Policy Evolution","date":"2020-08-05","arxiv_id":"2008.02387","repositories_listed":1,"syntology":null},{"url":"/paper/residual-force-control-for-agile-human","slug":"residual-force-control-for-agile-human","title":"Residual Force Control for Agile Human Behavior Imitation and Extended Motion Synthesis","date":"2020-06-12","arxiv_id":"2006.07364","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/residual-force-control-for-agile-human#ran","syntology_url":"https://syntology.ai/paper/2006.07364","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.07364"}},"official":{"repos":["Khrylx/RFC"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/optical-non-line-of-sight-physics-based-3d","slug":"optical-non-line-of-sight-physics-based-3d","title":"Optical Non-Line-of-Sight Physics-based 3D Human Pose Estimation","date":"2020-03-31","arxiv_id":"2003.14414","repositories_listed":1,"syntology":null},{"url":null,"slug":"kungfubot-physics-based-humanoid-whole-body","title":"KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills","date":"2025-06-15","arxiv_id":"2506.12851","repositories_listed":0,"syntology":null},{"url":null,"slug":"rl-from-physical-feedback-aligning-large","title":"RL from Physical Feedback: Aligning Large Motion Models with Humanoid Control","date":"2025-06-15","arxiv_id":"2506.12769","repositories_listed":0,"syntology":null},{"url":null,"slug":"bigger-regularized-categorical-high-capacity","title":"Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners","date":"2025-05-29","arxiv_id":"2505.23150","repositories_listed":0,"syntology":null},{"url":null,"slug":"fasttd3-simple-fast-and-capable-reinforcement","title":"FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Control","date":"2025-05-28","arxiv_id":"2505.22642","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-policy-but-many-worlds-a-scalable-unified","title":"One Policy but Many Worlds: A Scalable Unified Policy for Versatile Humanoid Locomotion","date":"2025-05-24","arxiv_id":"2505.18780","repositories_listed":0,"syntology":null},{"url":null,"slug":"hub-learning-extreme-humanoid-balance","title":"HuB: Learning Extreme Humanoid Balance","date":"2025-05-12","arxiv_id":"2505.07294","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-imitation-enables-contextual-humanoid","title":"Visual Imitation Enables Contextual Humanoid Control","date":"2025-05-06","arxiv_id":"2505.03729","repositories_listed":0,"syntology":null},{"url":null,"slug":"humanoid-vla-towards-universal-humanoid","title":"Humanoid-VLA: Towards Universal Humanoid Control with Visual Integration","date":"2025-02-20","arxiv_id":"2502.14795","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-bayesian-optimization-for-the-control-of","title":"Safe Bayesian Optimization for the Control of High-Dimensional Embodied Systems","date":"2024-12-29","arxiv_id":"2412.20350","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-from-massive-human-videos-for","title":"Learning from Massive Human Videos for Universal Humanoid Pose Control","date":"2024-12-18","arxiv_id":"2412.14172","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-with-action-sequence","title":"Coarse-to-fine Q-Network with Action Sequence for Data-Efficient Robot Learning","date":"2024-11-19","arxiv_id":"2411.12155","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-role-of-domain-randomization-in-training","title":"The Role of Domain Randomization in Training Diffusion Policies for Whole-Body Humanoid Control","date":"2024-11-02","arxiv_id":"2411.01349","repositories_listed":0,"syntology":null},{"url":null,"slug":"coohoi-learning-cooperative-human-object","title":"CooHOI: Learning Cooperative Human-Object Interaction with Manipulated Object Dynamics","date":"2024-06-20","arxiv_id":"2406.14558","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-world-models-as-visual-whole","title":"Hierarchical World Models as Visual Whole-Body Humanoid Controllers","date":"2024-05-28","arxiv_id":"2405.18418","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-simulated-avatar-from-head-mounted","title":"Real-Time Simulated Avatar from Head-Mounted Sensors","date":"2024-03-11","arxiv_id":"2403.06862","repositories_listed":0,"syntology":null},{"url":null,"slug":"humanoid-locomotion-as-next-token-prediction","title":"Humanoid Locomotion as Next Token Prediction","date":"2024-02-29","arxiv_id":"2402.19469","repositories_listed":0,"syntology":null},{"url":null,"slug":"h-gap-humanoid-control-with-a-generalist","title":"H-GAP: Humanoid Control with a Generalist Planner","date":"2023-12-05","arxiv_id":"2312.02682","repositories_listed":0,"syntology":null},{"url":null,"slug":"universal-humanoid-motion-representations-for","title":"Universal Humanoid Motion Representations for Physics-Based Control","date":"2023-10-06","arxiv_id":"2310.04582","repositories_listed":0,"syntology":null},{"url":null,"slug":"perpetual-humanoid-control-for-real-time","title":"Perpetual Humanoid Control for Real-time Simulated Avatars","date":"2023-05-10","arxiv_id":"2305.06456","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-universal-humanoid-control-to-automatic","title":"From Universal Humanoid Control to Automatic Physically Valid Character Creation","date":"2022-06-18","arxiv_id":"2206.09286","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploration-with-multi-sample-target-values","title":"Exploration with Multi-Sample Target Values for Distributional Reinforcement Learning","date":"2022-02-06","arxiv_id":"2202.02693","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-emergence-of-whole-body-strategies","title":"On the Emergence of Whole-body Strategies from Humanoid Robot Push-recovery Learning","date":"2021-04-29","arxiv_id":"2104.14534","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributionally-robust-trajectory","title":"Distributionally Robust Trajectory Optimization Under Uncertain Dynamics via Relative Entropy Trust-Regions","date":"2021-03-29","arxiv_id":"2103.15388","repositories_listed":0,"syntology":null},{"url":null,"slug":"rigorous-agent-evaluation-an-adversarial","title":"Rigorous Agent Evaluation: An Adversarial Approach to Uncover Catastrophic Failures","date":"2018-12-04","arxiv_id":"1812.01647","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-probabilistic-motor-primitives-for","title":"Neural probabilistic motor primitives for humanoid control","date":"2018-11-28","arxiv_id":"1811.11711","repositories_listed":0,"syntology":null}],"syntology_records":5,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":4,"papers_where_code_ran_first_page":"/task/humanoid-control/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/humanoid-control/papers/ran/1","json":"/task/humanoid-control/papers/ran/1.json","rows":4}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"c5aafd7aa54acdf334542660a3debf5571c3a712ea443be00d0ed346a157b452","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}