{"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/paired-open-ended-trailblazer-poet-endlessly","title":"Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions","arxiv_id":"1901.01753","date":"2019-01-07","proceeding":null,"authors":["Rui Wang","Joel Lehman","Jeff Clune","Kenneth O. Stanley"],"abstract":"While the history of machine learning so far largely encompasses a series of\nproblems posed by researchers and algorithms that learn their solutions, an\nimportant question is whether the problems themselves can be generated by the\nalgorithm at the same time as they are being solved. Such a process would in\neffect build its own diverse and expanding curricula, and the solutions to\nproblems at various stages would become stepping stones towards solving even\nmore challenging problems later in the process. The Paired Open-Ended\nTrailblazer (POET) algorithm introduced in this paper does just that: it pairs\nthe generation of environmental challenges and the optimization of agents to\nsolve those challenges. It simultaneously explores many different paths through\nthe space of possible problems and solutions and, critically, allows these\nstepping-stone solutions to transfer between problems if better, catalyzing\ninnovation. The term open-ended signifies the intriguing potential for\nalgorithms like POET to continue to create novel and increasingly complex\ncapabilities without bound. Our results show that POET produces a diverse range\nof sophisticated behaviors that solve a wide range of environmental challenges,\nmany of which cannot be solved by direct optimization alone, or even through a\ndirect-path curriculum-building control algorithm introduced to highlight the\ncritical role of open-endedness in solving ambitious challenges. The ability to\ntransfer solutions from one environment to another proves essential to\nunlocking the full potential of the system as a whole, demonstrating the\nunpredictable nature of fortuitous stepping stones. We hope that POET will\ninspire a new push towards open-ended discovery across many domains, where\nalgorithms like POET can blaze a trail through their interesting possible\nmanifestations and solutions.","url_abs":"http://arxiv.org/abs/1901.01753v3","url_pdf":"http://arxiv.org/pdf/1901.01753v3.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":"paired-open-ended-trailblazer-poet-endlessly","repo_url":"https://github.com/facebookresearch/dcd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"paired-open-ended-trailblazer-poet-endlessly","repo_url":"https://github.com/uber-research/poet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1901.01753","atlas_url":"https://app.syntology.ai/?focus=1901.01753","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.01753"}},"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/facebookresearch/dcd","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/uber-research/poet","reach":null}],"summary":{"ran_fixture":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":"71bce43475e27520","entry":"construct_niche_fns_from_env","repo":"uber-research/poet","repo_kind":"listed","path":"poet_distributed/poet_algo.py","file_url":"https://github.com/uber-research/poet/blob/HEAD/poet_distributed/poet_algo.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"71bce43475e27520"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}