{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:F75ZDXRVZYGU3AGCWS3BY6Q2CI","short_pith_number":"pith:F75ZDXRV","schema_version":"1.0","canonical_sha256":"2ffb91de35ce0d4d80c2b4b61c7a1a120c21dc6ac6a11dcf774b9267958a11df","source":{"kind":"arxiv","id":"2512.02019","version":3},"attestation_state":"computed","paper":{"title":"Diffusion-Augmented Markov Decision Processes for Maximum Entropy Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kaustubh Patil, Sebastian Sanokowski","submitted_at":"2025-12-01T18:59:58Z","abstract_excerpt":"Diffusion models excel at sampling from complex, unnormalized distributions. In this work, we extend Maximum Entropy Reinforcement Learning (ME-RL) to diffusion processes, enabling sampling from the optimal policy trajectory distribution. By minimizing a tractable upper bound on the reverse KL divergence between the diffusion policy and the optimal policy trajectory distributions, we derive a modified surrogate objective and introduce Diffusion-Augmented Markov Decision Processes (DA-MDPs). DA-MDPs allow for seamless integration of diffusion policies into any ME-RL method with minimal modifica"},"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":"2512.02019","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-12-01T18:59:58Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"1bd16195d8fcbebc445d901be461da8cbadad4fe97b943c68021d918c3005bd5","abstract_canon_sha256":"42a0839417d4a0fe92d729f0cac4b26d72d5efa2159d9d9a44b2f37a2031b599"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T02:04:44.670261Z","signature_b64":"Hc4LiHrctZIILlRFtqQpO7tsD5QudOLLKXCQ42h30I2DQ8wytp8aXVpPs7+63+GsBzZRkdNleoWr90ciricMBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ffb91de35ce0d4d80c2b4b61c7a1a120c21dc6ac6a11dcf774b9267958a11df","last_reissued_at":"2026-05-28T02:04:44.669599Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T02:04:44.669599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion-Augmented Markov Decision Processes for Maximum Entropy Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kaustubh Patil, Sebastian Sanokowski","submitted_at":"2025-12-01T18:59:58Z","abstract_excerpt":"Diffusion models excel at sampling from complex, unnormalized distributions. In this work, we extend Maximum Entropy Reinforcement Learning (ME-RL) to diffusion processes, enabling sampling from the optimal policy trajectory distribution. By minimizing a tractable upper bound on the reverse KL divergence between the diffusion policy and the optimal policy trajectory distributions, we derive a modified surrogate objective and introduce Diffusion-Augmented Markov Decision Processes (DA-MDPs). DA-MDPs allow for seamless integration of diffusion policies into any ME-RL method with minimal modifica"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.02019","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2512.02019/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2512.02019","created_at":"2026-05-28T02:04:44.669667+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.02019v3","created_at":"2026-05-28T02:04:44.669667+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.02019","created_at":"2026-05-28T02:04:44.669667+00:00"},{"alias_kind":"pith_short_12","alias_value":"F75ZDXRVZYGU","created_at":"2026-05-28T02:04:44.669667+00:00"},{"alias_kind":"pith_short_16","alias_value":"F75ZDXRVZYGU3AGC","created_at":"2026-05-28T02:04:44.669667+00:00"},{"alias_kind":"pith_short_8","alias_value":"F75ZDXRV","created_at":"2026-05-28T02:04:44.669667+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F75ZDXRVZYGU3AGCWS3BY6Q2CI","json":"https://pith.science/pith/F75ZDXRVZYGU3AGCWS3BY6Q2CI.json","graph_json":"https://pith.science/api/pith-number/F75ZDXRVZYGU3AGCWS3BY6Q2CI/graph.json","events_json":"https://pith.science/api/pith-number/F75ZDXRVZYGU3AGCWS3BY6Q2CI/events.json","paper":"https://pith.science/paper/F75ZDXRV"},"agent_actions":{"view_html":"https://pith.science/pith/F75ZDXRVZYGU3AGCWS3BY6Q2CI","download_json":"https://pith.science/pith/F75ZDXRVZYGU3AGCWS3BY6Q2CI.json","view_paper":"https://pith.science/paper/F75ZDXRV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.02019&json=true","fetch_graph":"https://pith.science/api/pith-number/F75ZDXRVZYGU3AGCWS3BY6Q2CI/graph.json","fetch_events":"https://pith.science/api/pith-number/F75ZDXRVZYGU3AGCWS3BY6Q2CI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F75ZDXRVZYGU3AGCWS3BY6Q2CI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F75ZDXRVZYGU3AGCWS3BY6Q2CI/action/storage_attestation","attest_author":"https://pith.science/pith/F75ZDXRVZYGU3AGCWS3BY6Q2CI/action/author_attestation","sign_citation":"https://pith.science/pith/F75ZDXRVZYGU3AGCWS3BY6Q2CI/action/citation_signature","submit_replication":"https://pith.science/pith/F75ZDXRVZYGU3AGCWS3BY6Q2CI/action/replication_record"}},"created_at":"2026-05-28T02:04:44.669667+00:00","updated_at":"2026-05-28T02:04:44.669667+00:00"}