{"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/imitating-human-behaviour-with-diffusion","title":"Imitating Human Behaviour with Diffusion Models","arxiv_id":"2301.10677","date":"2023-01-25","proceeding":null,"authors":["Tim Pearce","Tabish Rashid","Anssi Kanervisto","Dave Bignell","Mingfei Sun","Raluca Georgescu","Sergio Valcarcel Macua","Shan Zheng Tan","Ida Momennejad","Katja Hofmann","Sam Devlin"],"abstract":"Diffusion models have emerged as powerful generative models in the text-to-image domain. This paper studies their application as observation-to-action models for imitating human behaviour in sequential environments. Human behaviour is stochastic and multimodal, with structured correlations between action dimensions. Meanwhile, standard modelling choices in behaviour cloning are limited in their expressiveness and may introduce bias into the cloned policy. We begin by pointing out the limitations of these choices. We then propose that diffusion models are an excellent fit for imitating human behaviour, since they learn an expressive distribution over the joint action space. We introduce several innovations to make diffusion models suitable for sequential environments; designing suitable architectures, investigating the role of guidance, and developing reliable sampling strategies. Experimentally, diffusion models closely match human demonstrations in a simulated robotic control task and a modern 3D gaming environment.","url_abs":"https://arxiv.org/abs/2301.10677v2","url_pdf":"https://arxiv.org/pdf/2301.10677v2.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":"imitating-human-behaviour-with-diffusion","repo_url":"https://github.com/microsoft/imitating-human-behaviour-w-diffusion","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2301.10677","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.10677"}},"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/microsoft/imitating-human-behaviour-w-diffusion","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":4},"by_repo_kind":{"official":{"samples":5,"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":"f29345568db89515","entry":"matrix_diag","repo":"microsoft/imitating-human-behaviour-w-diffusion","repo_kind":"official","path":"code/models.py","file_url":"https://github.com/microsoft/imitating-human-behaviour-w-diffusion/blob/HEAD/code/models.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f29345568db89515"}},{"code_sha256_prefix":"9a16e3abe84897af","entry":"ddpm_schedules","repo":"microsoft/imitating-human-behaviour-w-diffusion","repo_kind":"official","path":"code/models.py","file_url":"https://github.com/microsoft/imitating-human-behaviour-w-diffusion/blob/HEAD/code/models.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":"9a16e3abe84897af"}},{"code_sha256_prefix":"5d9e485a37d3737f","entry":"get_random_offset","repo":"microsoft/imitating-human-behaviour-w-diffusion","repo_kind":"official","path":"code/make_dataset.py","file_url":"https://github.com/microsoft/imitating-human-behaviour-w-diffusion/blob/HEAD/code/make_dataset.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":"5d9e485a37d3737f"}},{"code_sha256_prefix":"c7c461dd154a4b37","entry":"rotate_image","repo":"microsoft/imitating-human-behaviour-w-diffusion","repo_kind":"official","path":"code/make_dataset.py","file_url":"https://github.com/microsoft/imitating-human-behaviour-w-diffusion/blob/HEAD/code/make_dataset.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":"c7c461dd154a4b37"}},{"code_sha256_prefix":"bf2dfa276aafa115","entry":"scale_image","repo":"microsoft/imitating-human-behaviour-w-diffusion","repo_kind":"official","path":"code/make_dataset.py","file_url":"https://github.com/microsoft/imitating-human-behaviour-w-diffusion/blob/HEAD/code/make_dataset.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":"bf2dfa276aafa115"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}