{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MFMFMCOOW6LMWSYDKBNN2HV4BW","short_pith_number":"pith:MFMFMCOO","schema_version":"1.0","canonical_sha256":"61585609ceb796cb4b03505add1ebc0db5caf821c4e12b7a9affbd03d2823f50","source":{"kind":"arxiv","id":"2602.06138","version":2},"attestation_state":"computed","paper":{"title":"Flow Matching for Offline Reinforcement Learning with Discrete Actions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Flow matching with continuous-time Markov chains recovers the optimal policy for offline RL with discrete actions under idealized conditions.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fairoz Nower Khan, Haibo Yang, Nabuat Zaman Nahim, Peizhong Ju, Ruiquan Huang","submitted_at":"2026-02-05T19:13:44Z","abstract_excerpt":"Generative policies based on diffusion models and flow matching have shown strong promise for offline reinforcement learning (RL), but their applicability remains largely confined to continuous action spaces. To address a broader range of offline RL settings, we extend flow matching to a general framework that supports discrete action spaces with multiple objectives. Specifically, we replace continuous flows with continuous-time Markov chains, trained using a Q-weighted flow matching objective. We then extend our design to multi-agent settings, mitigating the exponential growth of joint action"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2602.06138","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-05T19:13:44Z","cross_cats_sorted":[],"title_canon_sha256":"edd1c32da07207bd2adb1ae628d3824dd48dd46a905ebe0c5d9504ee225cd208","abstract_canon_sha256":"7873ca2cb6c902caf3f985d1bb5ba63fdb961700bedac3b36377cb032ad74207"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:23.801846Z","signature_b64":"ExzgJBw0Jl+nuGvksg7rpFlWkWjiPGuuDYls1NT+LxC7XC3fvQFkRDf3Vt3iPTOVErRiphDAiS3EL29zUkybAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61585609ceb796cb4b03505add1ebc0db5caf821c4e12b7a9affbd03d2823f50","last_reissued_at":"2026-05-18T03:09:23.801072Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:23.801072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flow Matching for Offline Reinforcement Learning with Discrete Actions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Flow matching with continuous-time Markov chains recovers the optimal policy for offline RL with discrete actions under idealized conditions.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fairoz Nower Khan, Haibo Yang, Nabuat Zaman Nahim, Peizhong Ju, Ruiquan Huang","submitted_at":"2026-02-05T19:13:44Z","abstract_excerpt":"Generative policies based on diffusion models and flow matching have shown strong promise for offline reinforcement learning (RL), but their applicability remains largely confined to continuous action spaces. To address a broader range of offline RL settings, we extend flow matching to a general framework that supports discrete action spaces with multiple objectives. Specifically, we replace continuous flows with continuous-time Markov chains, trained using a Q-weighted flow matching objective. We then extend our design to multi-agent settings, mitigating the exponential growth of joint action"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We theoretically show that, under idealized conditions, optimizing this objective recovers the optimal policy.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The idealized conditions required for the theoretical recovery of the optimal policy via the Q-weighted flow matching objective on continuous-time Markov chains.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Flow matching is adapted to discrete actions via continuous-time Markov chains and Q-weighted objectives, recovering optimal policies under idealized conditions and outperforming baselines in multi-agent and multi-objective offline RL experiments.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Flow matching with continuous-time Markov chains recovers the optimal policy for offline RL with discrete actions under idealized conditions.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"257b3c19fed51e739de024701a9845a8ff131855ca4c1e688c555be4955e9c8b"},"source":{"id":"2602.06138","kind":"arxiv","version":2},"verdict":{"id":"a0619a25-7229-4b5d-abfb-ad74b8166353","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T06:36:26.134774Z","strongest_claim":"We theoretically show that, under idealized conditions, optimizing this objective recovers the optimal policy.","one_line_summary":"Flow matching is adapted to discrete actions via continuous-time Markov chains and Q-weighted objectives, recovering optimal policies under idealized conditions and outperforming baselines in multi-agent and multi-objective offline RL experiments.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The idealized conditions required for the theoretical recovery of the optimal policy via the Q-weighted flow matching objective on continuous-time Markov chains.","pith_extraction_headline":"Flow matching with continuous-time Markov chains recovers the optimal policy for offline RL with discrete actions under idealized conditions."},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2602.06138","created_at":"2026-05-18T03:09:23.801200+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.06138v2","created_at":"2026-05-18T03:09:23.801200+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.06138","created_at":"2026-05-18T03:09:23.801200+00:00"},{"alias_kind":"pith_short_12","alias_value":"MFMFMCOOW6LM","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"MFMFMCOOW6LMWSYD","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"MFMFMCOO","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.12805","citing_title":"Discrete MeanFlow: One-Step Generation via Conditional Transition Kernels","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12379","citing_title":"Discrete Flow Matching for Offline-to-Online Reinforcement Learning","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MFMFMCOOW6LMWSYDKBNN2HV4BW","json":"https://pith.science/pith/MFMFMCOOW6LMWSYDKBNN2HV4BW.json","graph_json":"https://pith.science/api/pith-number/MFMFMCOOW6LMWSYDKBNN2HV4BW/graph.json","events_json":"https://pith.science/api/pith-number/MFMFMCOOW6LMWSYDKBNN2HV4BW/events.json","paper":"https://pith.science/paper/MFMFMCOO"},"agent_actions":{"view_html":"https://pith.science/pith/MFMFMCOOW6LMWSYDKBNN2HV4BW","download_json":"https://pith.science/pith/MFMFMCOOW6LMWSYDKBNN2HV4BW.json","view_paper":"https://pith.science/paper/MFMFMCOO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.06138&json=true","fetch_graph":"https://pith.science/api/pith-number/MFMFMCOOW6LMWSYDKBNN2HV4BW/graph.json","fetch_events":"https://pith.science/api/pith-number/MFMFMCOOW6LMWSYDKBNN2HV4BW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MFMFMCOOW6LMWSYDKBNN2HV4BW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MFMFMCOOW6LMWSYDKBNN2HV4BW/action/storage_attestation","attest_author":"https://pith.science/pith/MFMFMCOOW6LMWSYDKBNN2HV4BW/action/author_attestation","sign_citation":"https://pith.science/pith/MFMFMCOOW6LMWSYDKBNN2HV4BW/action/citation_signature","submit_replication":"https://pith.science/pith/MFMFMCOOW6LMWSYDKBNN2HV4BW/action/replication_record"}},"created_at":"2026-05-18T03:09:23.801200+00:00","updated_at":"2026-05-18T03:09:23.801200+00:00"}