{"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/gflownet-training-by-policy-gradients","title":"GFlowNet Training by Policy Gradients","arxiv_id":"2408.05885","date":"2024-08-12","proceeding":null,"authors":["Puhua Niu","Shili Wu","Mingzhou Fan","Xiaoning Qian"],"abstract":"Generative Flow Networks (GFlowNets) have been shown effective to generate combinatorial objects with desired properties. We here propose a new GFlowNet training framework, with policy-dependent rewards, that bridges keeping flow balance of GFlowNets to optimizing the expected accumulated reward in traditional Reinforcement-Learning (RL). This enables the derivation of new policy-based GFlowNet training methods, in contrast to existing ones resembling value-based RL. It is known that the design of backward policies in GFlowNet training affects efficiency. We further develop a coupled training strategy that jointly solves GFlowNet forward policy training and backward policy design. Performance analysis is provided with a theoretical guarantee of our policy-based GFlowNet training. Experiments on both simulated and real-world datasets verify that our policy-based strategies provide advanced RL perspectives for robust gradient estimation to improve GFlowNet performance.","url_abs":"https://arxiv.org/abs/2408.05885v1","url_pdf":"https://arxiv.org/pdf/2408.05885v1.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":"gflownet-training-by-policy-gradients","repo_url":"https://github.com/niupuhua1234/gfn-pg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2408.05885","atlas_url":"https://app.syntology.ai/?focus=2408.05885","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.05885"}},"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/niupuhua1234/gfn-pg","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"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":4,"samples":[{"code_sha256_prefix":"874cb43146e2c04f","entry":"download","repo":"niupuhua1234/gfn-pg","repo_kind":"official","path":"gfn-pg/data_dag/data.py","file_url":"https://github.com/niupuhua1234/gfn-pg/blob/HEAD/gfn-pg/data_dag/data.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"874cb43146e2c04f"}},{"code_sha256_prefix":"a2b19bef0331f930","entry":"ix_","repo":"niupuhua1234/gfn-pg","repo_kind":"official","path":"gfn-pg/data_dag/scores/base.py","file_url":"https://github.com/niupuhua1234/gfn-pg/blob/HEAD/gfn-pg/data_dag/scores/base.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a2b19bef0331f930"}},{"code_sha256_prefix":"0cb1419ec492cafd","entry":"logdet","repo":"niupuhua1234/gfn-pg","repo_kind":"official","path":"gfn-pg/data_dag/scores/base.py","file_url":"https://github.com/niupuhua1234/gfn-pg/blob/HEAD/gfn-pg/data_dag/scores/base.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0cb1419ec492cafd"}},{"code_sha256_prefix":"52ac2620e1dc4258","entry":"logdet","repo":"niupuhua1234/gfn-pg","repo_kind":"official","path":"gfn-pg/data_dag/scores/base_torch.py","file_url":"https://github.com/niupuhua1234/gfn-pg/blob/HEAD/gfn-pg/data_dag/scores/base_torch.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"52ac2620e1dc4258"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}