{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PYNKQX6UTILPKIXSFILCXP466Z","short_pith_number":"pith:PYNKQX6U","schema_version":"1.0","canonical_sha256":"7e1aa85fd49a16f522f22a162bbf9ef66c0b4795c8a6174d115ad1af82d68e7a","source":{"kind":"arxiv","id":"2510.03508","version":3},"attestation_state":"computed","paper":{"title":"D2 Actor Critic: Diffusion Actor Meets Distributional Critic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bradly C Stadie, Hanrui Lyu, Lunjun Zhang, Shuo Han","submitted_at":"2025-10-03T20:47:24Z","abstract_excerpt":"We introduce D2AC, a new model-free reinforcement learning (RL) algorithm designed to train expressive diffusion policies online effectively. At its core is a policy improvement objective that avoids the high variance of typical policy gradients and the complexity of backpropagation through time. This stable learning process is critically enabled by our second contribution: a robust distributional critic, which we design through a fusion of distributional RL and clipped double Q-learning. The resulting algorithm is highly effective, achieving state-of-the-art performance on a benchmark of eigh"},"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":"2510.03508","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-03T20:47:24Z","cross_cats_sorted":[],"title_canon_sha256":"1ba313632cfd637a60b2c81faf4a1722775b3a161ee425ffaffc17a4eb21a8a3","abstract_canon_sha256":"4be3001d065804074a2300272b7a1f4d17c35b42bd1467d813946e20634ad39a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:07.820945Z","signature_b64":"cyyIqgt86B23anTNg+VrJtfS4A8emQKc7CRVyd4WyzWPJ3hnEPczh4adu8USYzCqIJqfrz1reP4xKeINt2YECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e1aa85fd49a16f522f22a162bbf9ef66c0b4795c8a6174d115ad1af82d68e7a","last_reissued_at":"2026-05-25T02:01:07.819997Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:07.819997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"D2 Actor Critic: Diffusion Actor Meets Distributional Critic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bradly C Stadie, Hanrui Lyu, Lunjun Zhang, Shuo Han","submitted_at":"2025-10-03T20:47:24Z","abstract_excerpt":"We introduce D2AC, a new model-free reinforcement learning (RL) algorithm designed to train expressive diffusion policies online effectively. At its core is a policy improvement objective that avoids the high variance of typical policy gradients and the complexity of backpropagation through time. This stable learning process is critically enabled by our second contribution: a robust distributional critic, which we design through a fusion of distributional RL and clipped double Q-learning. The resulting algorithm is highly effective, achieving state-of-the-art performance on a benchmark of eigh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.03508","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/2510.03508/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":"2510.03508","created_at":"2026-05-25T02:01:07.820122+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.03508v3","created_at":"2026-05-25T02:01:07.820122+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.03508","created_at":"2026-05-25T02:01:07.820122+00:00"},{"alias_kind":"pith_short_12","alias_value":"PYNKQX6UTILP","created_at":"2026-05-25T02:01:07.820122+00:00"},{"alias_kind":"pith_short_16","alias_value":"PYNKQX6UTILPKIXS","created_at":"2026-05-25T02:01:07.820122+00:00"},{"alias_kind":"pith_short_8","alias_value":"PYNKQX6U","created_at":"2026-05-25T02:01:07.820122+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/PYNKQX6UTILPKIXSFILCXP466Z","json":"https://pith.science/pith/PYNKQX6UTILPKIXSFILCXP466Z.json","graph_json":"https://pith.science/api/pith-number/PYNKQX6UTILPKIXSFILCXP466Z/graph.json","events_json":"https://pith.science/api/pith-number/PYNKQX6UTILPKIXSFILCXP466Z/events.json","paper":"https://pith.science/paper/PYNKQX6U"},"agent_actions":{"view_html":"https://pith.science/pith/PYNKQX6UTILPKIXSFILCXP466Z","download_json":"https://pith.science/pith/PYNKQX6UTILPKIXSFILCXP466Z.json","view_paper":"https://pith.science/paper/PYNKQX6U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.03508&json=true","fetch_graph":"https://pith.science/api/pith-number/PYNKQX6UTILPKIXSFILCXP466Z/graph.json","fetch_events":"https://pith.science/api/pith-number/PYNKQX6UTILPKIXSFILCXP466Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PYNKQX6UTILPKIXSFILCXP466Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PYNKQX6UTILPKIXSFILCXP466Z/action/storage_attestation","attest_author":"https://pith.science/pith/PYNKQX6UTILPKIXSFILCXP466Z/action/author_attestation","sign_citation":"https://pith.science/pith/PYNKQX6UTILPKIXSFILCXP466Z/action/citation_signature","submit_replication":"https://pith.science/pith/PYNKQX6UTILPKIXSFILCXP466Z/action/replication_record"}},"created_at":"2026-05-25T02:01:07.820122+00:00","updated_at":"2026-05-25T02:01:07.820122+00:00"}