{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HYW5UXUEU7WCFJVFOC74OFJ77H","short_pith_number":"pith:HYW5UXUE","schema_version":"1.0","canonical_sha256":"3e2dda5e84a7ec22a6a570bfc7153ff9f1b137a40b506d05da7670d31cc1bafa","source":{"kind":"arxiv","id":"2606.22630","version":1},"attestation_state":"computed","paper":{"title":"Scalable Maximum Entropy Reinforcement Learning for Diffusion Policies via Adjoint Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Denis Blessing, Emiliyan Gospodinov, Gerhard Neumann, Onur Celik, Serge Thilges","submitted_at":"2026-06-21T18:32:25Z","abstract_excerpt":"Diffusion policies have recently emerged as a powerful paradigm for representing complex action distributions in reinforcement learning (RL). However, their application to online RL remains limited by the challenge of scalable training in the absence of ground-truth data, where standard optimization techniques such as score matching are not directly applicable. In this work, we introduce a highly efficient algorithm for optimizing diffusion policies by leveraging recent advances in stochastic optimal control. Our approach is based on adjoint matching, which enables simulation-free training and"},"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":"2606.22630","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-21T18:32:25Z","cross_cats_sorted":[],"title_canon_sha256":"194aa3db71b87183ec928f6c97c356460fcc37e5337f464eb5c2ee2811c0bc34","abstract_canon_sha256":"e28c0b1a520957b68a9c3499f80a4d90eb4e3b5e2c4e6323bbac4fc720a08bf1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:43.543990Z","signature_b64":"Fp3nk0zUoVTCL4JPzTsLSKv63T3yboLU8XhVSOsWDtI4JtNiMn2kWqHIzwIQjASv0mCUGHANl4ybd0pRj2NlBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e2dda5e84a7ec22a6a570bfc7153ff9f1b137a40b506d05da7670d31cc1bafa","last_reissued_at":"2026-06-23T02:13:43.543603Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:43.543603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable Maximum Entropy Reinforcement Learning for Diffusion Policies via Adjoint Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Denis Blessing, Emiliyan Gospodinov, Gerhard Neumann, Onur Celik, Serge Thilges","submitted_at":"2026-06-21T18:32:25Z","abstract_excerpt":"Diffusion policies have recently emerged as a powerful paradigm for representing complex action distributions in reinforcement learning (RL). However, their application to online RL remains limited by the challenge of scalable training in the absence of ground-truth data, where standard optimization techniques such as score matching are not directly applicable. In this work, we introduce a highly efficient algorithm for optimizing diffusion policies by leveraging recent advances in stochastic optimal control. Our approach is based on adjoint matching, which enables simulation-free training and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22630","kind":"arxiv","version":1},"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/2606.22630/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":"2606.22630","created_at":"2026-06-23T02:13:43.543670+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.22630v1","created_at":"2026-06-23T02:13:43.543670+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22630","created_at":"2026-06-23T02:13:43.543670+00:00"},{"alias_kind":"pith_short_12","alias_value":"HYW5UXUEU7WC","created_at":"2026-06-23T02:13:43.543670+00:00"},{"alias_kind":"pith_short_16","alias_value":"HYW5UXUEU7WCFJVF","created_at":"2026-06-23T02:13:43.543670+00:00"},{"alias_kind":"pith_short_8","alias_value":"HYW5UXUE","created_at":"2026-06-23T02:13:43.543670+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/HYW5UXUEU7WCFJVFOC74OFJ77H","json":"https://pith.science/pith/HYW5UXUEU7WCFJVFOC74OFJ77H.json","graph_json":"https://pith.science/api/pith-number/HYW5UXUEU7WCFJVFOC74OFJ77H/graph.json","events_json":"https://pith.science/api/pith-number/HYW5UXUEU7WCFJVFOC74OFJ77H/events.json","paper":"https://pith.science/paper/HYW5UXUE"},"agent_actions":{"view_html":"https://pith.science/pith/HYW5UXUEU7WCFJVFOC74OFJ77H","download_json":"https://pith.science/pith/HYW5UXUEU7WCFJVFOC74OFJ77H.json","view_paper":"https://pith.science/paper/HYW5UXUE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.22630&json=true","fetch_graph":"https://pith.science/api/pith-number/HYW5UXUEU7WCFJVFOC74OFJ77H/graph.json","fetch_events":"https://pith.science/api/pith-number/HYW5UXUEU7WCFJVFOC74OFJ77H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HYW5UXUEU7WCFJVFOC74OFJ77H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HYW5UXUEU7WCFJVFOC74OFJ77H/action/storage_attestation","attest_author":"https://pith.science/pith/HYW5UXUEU7WCFJVFOC74OFJ77H/action/author_attestation","sign_citation":"https://pith.science/pith/HYW5UXUEU7WCFJVFOC74OFJ77H/action/citation_signature","submit_replication":"https://pith.science/pith/HYW5UXUEU7WCFJVFOC74OFJ77H/action/replication_record"}},"created_at":"2026-06-23T02:13:43.543670+00:00","updated_at":"2026-06-23T02:13:43.543670+00:00"}