{"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/intrinsic-motivation-and-automatic-curricula","title":"Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play","arxiv_id":"1703.05407","date":"2017-03-15","proceeding":"ICLR 2018 1","authors":["Sainbayar Sukhbaatar","Zeming Lin","Ilya Kostrikov","Gabriel Synnaeve","Arthur Szlam","Rob Fergus"],"abstract":"We describe a simple scheme that allows an agent to learn about its\nenvironment in an unsupervised manner. Our scheme pits two versions of the same\nagent, Alice and Bob, against one another. Alice proposes a task for Bob to\ncomplete; and then Bob attempts to complete the task. In this work we will\nfocus on two kinds of environments: (nearly) reversible environments and\nenvironments that can be reset. Alice will \"propose\" the task by doing a\nsequence of actions and then Bob must undo or repeat them, respectively. Via an\nappropriate reward structure, Alice and Bob automatically generate a curriculum\nof exploration, enabling unsupervised training of the agent. When Bob is\ndeployed on an RL task within the environment, this unsupervised training\nreduces the number of supervised episodes needed to learn, and in some cases\nconverges to a higher reward.","url_abs":"http://arxiv.org/abs/1703.05407v5","url_pdf":"http://arxiv.org/pdf/1703.05407v5.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":"intrinsic-motivation-and-automatic-curricula","repo_url":"https://github.com/ACampero/hsp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"intrinsic-motivation-and-automatic-curricula","repo_url":"https://github.com/shagunsodhani/memory-augmented-self-play","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"intrinsic-motivation-and-automatic-curricula","repo_url":"https://github.com/tesatory/hsp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1703.05407","atlas_url":"https://app.syntology.ai/?focus=1703.05407","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.05407"}},"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/tesatory/hsp","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ACampero/hsp","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shagunsodhani/memory-augmented-self-play","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":1,"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":"4ef105d67c1592bc","entry":"run_target_episode","repo":"shagunsodhani/memory-augmented-self-play","repo_kind":"listed","path":"SelfPlay/app/selfplay.py","file_url":"https://github.com/shagunsodhani/memory-augmented-self-play/blob/HEAD/SelfPlay/app/selfplay.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":"4ef105d67c1592bc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}