{"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/qgfn-controllable-greediness-with-action","title":"QGFN: Controllable Greediness with Action Values","arxiv_id":"2402.05234","date":"2024-02-07","proceeding":null,"authors":["Elaine Lau","Stephen Zhewen Lu","Ling Pan","Doina Precup","Emmanuel Bengio"],"abstract":"Generative Flow Networks (GFlowNets; GFNs) are a family of energy-based generative methods for combinatorial objects, capable of generating diverse and high-utility samples. However, consistently biasing GFNs towards producing high-utility samples is non-trivial. In this work, we leverage connections between GFNs and reinforcement learning (RL) and propose to combine the GFN policy with an action-value estimate, $Q$, to create greedier sampling policies which can be controlled by a mixing parameter. We show that several variants of the proposed method, QGFN, are able to improve on the number of high-reward samples generated in a variety of tasks without sacrificing diversity.","url_abs":"https://arxiv.org/abs/2402.05234v3","url_pdf":"https://arxiv.org/pdf/2402.05234v3.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":"qgfn-controllable-greediness-with-action","repo_url":"https://github.com/yunglau/QGFN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.05234","atlas_url":"https://app.syntology.ai/?focus=2402.05234","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05234"}},"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":"deterministic:regex_extraction","url":"https://github.com/yunglau/QGFN","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":6,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"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":"42c82ab33c19b894","entry":"aggregate_iqm","repo":"yunglau/QGFN","repo_kind":"official","path":"utils/metrics.py","file_url":"https://github.com/yunglau/QGFN/blob/HEAD/utils/metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"42c82ab33c19b894"}},{"code_sha256_prefix":"31cec085da1cc1c5","entry":"get_groupby_value","repo":"yunglau/QGFN","repo_kind":"official","path":"utils/metrics.py","file_url":"https://github.com/yunglau/QGFN/blob/HEAD/utils/metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"31cec085da1cc1c5"}},{"code_sha256_prefix":"5dc95db4192ee1e6","entry":"make_sh_script","repo":"yunglau/QGFN","repo_kind":"official","path":"utils/runs.py","file_url":"https://github.com/yunglau/QGFN/blob/HEAD/utils/runs.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5dc95db4192ee1e6"}},{"code_sha256_prefix":"40f2f8185e2b1e3f","entry":"mean_confidence_interval","repo":"yunglau/QGFN","repo_kind":"official","path":"utils/metrics.py","file_url":"https://github.com/yunglau/QGFN/blob/HEAD/utils/metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"40f2f8185e2b1e3f"}},{"code_sha256_prefix":"d8821f0b8834c2ef","entry":"scheduler","repo":"yunglau/qgfn","repo_kind":"official","path":"src/gflownet/data/mix_iterator.py","file_url":"https://github.com/yunglau/qgfn/blob/HEAD/src/gflownet/data/mix_iterator.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d8821f0b8834c2ef"}},{"code_sha256_prefix":"6e3e278b5881d761","entry":"sqlite_load","repo":"yunglau/QGFN","repo_kind":"official","path":"utils/loaders.py","file_url":"https://github.com/yunglau/QGFN/blob/HEAD/utils/loaders.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6e3e278b5881d761"}},{"code_sha256_prefix":"70d87c0cd02ff899","entry":"try_to_load_df","repo":"yunglau/QGFN","repo_kind":"official","path":"utils/plotting.py","file_url":"https://github.com/yunglau/QGFN/blob/HEAD/utils/plotting.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"70d87c0cd02ff899"}},{"code_sha256_prefix":"30dd48f7c0ea8071","entry":"rna_sqlite_load","repo":"yunglau/QGFN","repo_kind":"official","path":"utils/loaders.py","file_url":"https://github.com/yunglau/QGFN/blob/HEAD/utils/loaders.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":"30dd48f7c0ea8071"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}