{"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/distributional-gflownets-with-quantile-flows","title":"Distributional GFlowNets with Quantile Flows","arxiv_id":"2302.05793","date":"2023-02-11","proceeding":null,"authors":["Dinghuai Zhang","Ling Pan","Ricky T. Q. Chen","Aaron Courville","Yoshua Bengio"],"abstract":"Generative Flow Networks (GFlowNets) are a new family of probabilistic samplers where an agent learns a stochastic policy for generating complex combinatorial structure through a series of decision-making steps. Despite being inspired from reinforcement learning, the current GFlowNet framework is relatively limited in its applicability and cannot handle stochasticity in the reward function. In this work, we adopt a distributional paradigm for GFlowNets, turning each flow function into a distribution, thus providing more informative learning signals during training. By parameterizing each edge flow through their quantile functions, our proposed \\textit{quantile matching} GFlowNet learning algorithm is able to learn a risk-sensitive policy, an essential component for handling scenarios with risk uncertainty. Moreover, we find that the distributional approach can achieve substantial improvement on existing benchmarks compared to prior methods due to our enhanced training algorithm, even in settings with deterministic rewards.","url_abs":"https://arxiv.org/abs/2302.05793v3","url_pdf":"https://arxiv.org/pdf/2302.05793v3.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":"distributional-gflownets-with-quantile-flows","repo_url":"https://github.com/zdhnarsil/distributional-gflownets","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2302.05793","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.05793"}},"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/zdhnarsil/distributional-gflownets","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":12},"by_repo_kind":{"official":{"samples":14,"ran":2,"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":"6b452c8d0cc45c99","entry":"edge_match","repo":"zdhnarsil/distributional-gflownets","repo_kind":"official","path":"mols/mol_mdp_ext.py","file_url":"https://github.com/zdhnarsil/distributional-gflownets/blob/HEAD/mols/mol_mdp_ext.py","link_basis":"harvester_set","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":"6b452c8d0cc45c99"}},{"code_sha256_prefix":"514f704ea4cae3e4","entry":"node_match","repo":"zdhnarsil/distributional-gflownets","repo_kind":"official","path":"mols/mol_mdp_ext.py","file_url":"https://github.com/zdhnarsil/distributional-gflownets/blob/HEAD/mols/mol_mdp_ext.py","link_basis":"harvester_set","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":"514f704ea4cae3e4"}},{"code_sha256_prefix":"6f514da43ddcc0a0","entry":"detailed_balance_loss","repo":"zdhnarsil/distributional-gflownets","repo_kind":"official","path":"mols/gflownet.py","file_url":"https://github.com/zdhnarsil/distributional-gflownets/blob/HEAD/mols/gflownet.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":"6f514da43ddcc0a0"}},{"code_sha256_prefix":"4f978fbee1d9c9b2","entry":"func_diff_corners","repo":"zdhnarsil/distributional-gflownets","repo_kind":"official","path":"grid/toy_grid_dag.py","file_url":"https://github.com/zdhnarsil/distributional-gflownets/blob/HEAD/grid/toy_grid_dag.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":"4f978fbee1d9c9b2"}},{"code_sha256_prefix":"f6c0e2ad8348ec59","entry":"get_func","repo":"zdhnarsil/distributional-gflownets","repo_kind":"official","path":"grid/toy_grid_dag.py","file_url":"https://github.com/zdhnarsil/distributional-gflownets/blob/HEAD/grid/toy_grid_dag.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":"f6c0e2ad8348ec59"}},{"code_sha256_prefix":"29e96c8a8bdeae38","entry":"make_mlp","repo":"zdhnarsil/distributional-gflownets","repo_kind":"official","path":"grid/distributional.py","file_url":"https://github.com/zdhnarsil/distributional-gflownets/blob/HEAD/grid/distributional.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":"29e96c8a8bdeae38"}},{"code_sha256_prefix":"5c990a0f4e743885","entry":"mol2graph","repo":"zdhnarsil/distributional-gflownets","repo_kind":"official","path":"mols/model_block.py","file_url":"https://github.com/zdhnarsil/distributional-gflownets/blob/HEAD/mols/model_block.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":"5c990a0f4e743885"}},{"code_sha256_prefix":"06477cbf36090384","entry":"mols2batch","repo":"zdhnarsil/distributional-gflownets","repo_kind":"official","path":"mols/model_atom.py","file_url":"https://github.com/zdhnarsil/distributional-gflownets/blob/HEAD/mols/model_atom.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":"06477cbf36090384"}},{"code_sha256_prefix":"e2f61d62c1a23b4e","entry":"mols2batch","repo":"zdhnarsil/distributional-gflownets","repo_kind":"official","path":"mols/model_block.py","file_url":"https://github.com/zdhnarsil/distributional-gflownets/blob/HEAD/mols/model_block.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":"e2f61d62c1a23b4e"}},{"code_sha256_prefix":"00732f3acab6fcc3","entry":"normal_cdf","repo":"zdhnarsil/distributional-gflownets","repo_kind":"official","path":"grid/distributional.py","file_url":"https://github.com/zdhnarsil/distributional-gflownets/blob/HEAD/grid/distributional.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":"00732f3acab6fcc3"}},{"code_sha256_prefix":"85f30989270c06ff","entry":"normal_invcdf","repo":"zdhnarsil/distributional-gflownets","repo_kind":"official","path":"grid/distributional.py","file_url":"https://github.com/zdhnarsil/distributional-gflownets/blob/HEAD/grid/distributional.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":"85f30989270c06ff"}},{"code_sha256_prefix":"a0579acf3f4c545c","entry":"onehot","repo":"zdhnarsil/distributional-gflownets","repo_kind":"official","path":"mols/utils/chem.py","file_url":"https://github.com/zdhnarsil/distributional-gflownets/blob/HEAD/mols/utils/chem.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":"a0579acf3f4c545c"}},{"code_sha256_prefix":"f267c62af541e3d2","entry":"tb_lambda_loss","repo":"zdhnarsil/distributional-gflownets","repo_kind":"official","path":"mols/gflownet.py","file_url":"https://github.com/zdhnarsil/distributional-gflownets/blob/HEAD/mols/gflownet.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":"f267c62af541e3d2"}},{"code_sha256_prefix":"e4f0eb023588e4fc","entry":"trajectory_balance_loss","repo":"zdhnarsil/distributional-gflownets","repo_kind":"official","path":"mols/gflownet.py","file_url":"https://github.com/zdhnarsil/distributional-gflownets/blob/HEAD/mols/gflownet.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":"e4f0eb023588e4fc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}