{"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/what-matters-in-learning-from-offline-human","title":"What Matters in Learning from Offline Human Demonstrations for Robot Manipulation","arxiv_id":"2108.03298","date":"2021-08-06","proceeding":null,"authors":["Ajay Mandlekar","Danfei Xu","Josiah Wong","Soroush Nasiriany","Chen Wang","Rohun Kulkarni","Li Fei-Fei","Silvio Savarese","Yuke Zhu","Roberto Martín-Martín"],"abstract":"Imitating human demonstrations is a promising approach to endow robots with various manipulation capabilities. While recent advances have been made in imitation learning and batch (offline) reinforcement learning, a lack of open-source human datasets and reproducible learning methods make assessing the state of the field difficult. In this paper, we conduct an extensive study of six offline learning algorithms for robot manipulation on five simulated and three real-world multi-stage manipulation tasks of varying complexity, and with datasets of varying quality. Our study analyzes the most critical challenges when learning from offline human data for manipulation. Based on the study, we derive a series of lessons including the sensitivity to different algorithmic design choices, the dependence on the quality of the demonstrations, and the variability based on the stopping criteria due to the different objectives in training and evaluation. We also highlight opportunities for learning from human datasets, such as the ability to learn proficient policies on challenging, multi-stage tasks beyond the scope of current reinforcement learning methods, and the ability to easily scale to natural, real-world manipulation scenarios where only raw sensory signals are available. We have open-sourced our datasets and all algorithm implementations to facilitate future research and fair comparisons in learning from human demonstration data. Codebase, datasets, trained models, and more available at https://arise-initiative.github.io/robomimic-web/","url_abs":"https://arxiv.org/abs/2108.03298v2","url_pdf":"https://arxiv.org/pdf/2108.03298v2.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":"what-matters-in-learning-from-offline-human","repo_url":"https://github.com/ARISE-Initiative/robomimic","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"imitation-learning","task_name":"Imitation Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"robot-manipulation","task_name":"Robot Manipulation"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/robot-manipulation-on-mimicgen","task":"Robot Manipulation","dataset":"MimicGen","model":"BC RNN (Evaluated in EquiDiff)","rank_in_archive_order":6,"of":7,"metrics":{"Succ. Rate (12 tasks, 100 demo/task)":"22.9","Succ. Rate (12 tasks, 1000 demo/task)":"70.3","Succ. Rate (12 tasks, 200 demo/task)":"41.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2108.03298","atlas_url":"https://app.syntology.ai/?focus=2108.03298","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.03298"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/ARISE-Initiative/robomimic","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"listed":{"samples":3,"ran":1,"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":"1db8c13e93e6d733","entry":"register_algo_factory_func","repo":"ARISE-Initiative/robomimic","repo_kind":"listed","path":"robomimic/algo/algo.py","file_url":"https://github.com/ARISE-Initiative/robomimic/blob/HEAD/robomimic/algo/algo.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1db8c13e93e6d733"}},{"code_sha256_prefix":"c9dad182621b681d","entry":"algo_factory","repo":"ARISE-Initiative/robomimic","repo_kind":"listed","path":"robomimic/algo/algo.py","file_url":"https://github.com/ARISE-Initiative/robomimic/blob/HEAD/robomimic/algo/algo.py","link_basis":"first_harvest_node","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":"c9dad182621b681d"}},{"code_sha256_prefix":"16f37e2539e0aca4","entry":"algo_name_to_factory_func","repo":"ARISE-Initiative/robomimic","repo_kind":"listed","path":"robomimic/algo/algo.py","file_url":"https://github.com/ARISE-Initiative/robomimic/blob/HEAD/robomimic/algo/algo.py","link_basis":"first_harvest_node","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":"16f37e2539e0aca4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}