{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6N5IGTYCSLLTHDCSY5SX756QQO","short_pith_number":"pith:6N5IGTYC","schema_version":"1.0","canonical_sha256":"f37a834f0292d7338c52c7657ff7d083ad33a20ff9a9cc9734d735a015f00951","source":{"kind":"arxiv","id":"2310.06343","version":2},"attestation_state":"computed","paper":{"title":"Boosting Continuous Control with Consistency Policy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dongbin Zhao, Haoran Li, Yuhui Chen","submitted_at":"2023-10-10T06:26:05Z","abstract_excerpt":"Due to its training stability and strong expression, the diffusion model has attracted considerable attention in offline reinforcement learning. However, several challenges have also come with it: 1) The demand for a large number of diffusion steps makes the diffusion-model-based methods time inefficient and limits their applications in real-time control; 2) How to achieve policy improvement with accurate guidance for diffusion model-based policy is still an open problem. Inspired by the consistency model, we propose a novel time-efficiency method named Consistency Policy with Q-Learning (CPQL"},"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":"2310.06343","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-10T06:26:05Z","cross_cats_sorted":[],"title_canon_sha256":"b8453a5ad6785994b13da8e52bbd2b00c4cb61802826ea383c8b4ec80e4726d0","abstract_canon_sha256":"da09b3937d21d83751158238ede4055c6b3d7c022e5044fdaeea9687947063cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:55.133758Z","signature_b64":"AJApCwouhGD8tufw8EFe3xtroAOS+7uVndB+9Z0RDRiOheVkqgJWb4LuCeR7/koIwqVXaG5eDNUzV/ngWf5/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f37a834f0292d7338c52c7657ff7d083ad33a20ff9a9cc9734d735a015f00951","last_reissued_at":"2026-07-05T07:36:55.133231Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:55.133231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boosting Continuous Control with Consistency Policy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dongbin Zhao, Haoran Li, Yuhui Chen","submitted_at":"2023-10-10T06:26:05Z","abstract_excerpt":"Due to its training stability and strong expression, the diffusion model has attracted considerable attention in offline reinforcement learning. However, several challenges have also come with it: 1) The demand for a large number of diffusion steps makes the diffusion-model-based methods time inefficient and limits their applications in real-time control; 2) How to achieve policy improvement with accurate guidance for diffusion model-based policy is still an open problem. Inspired by the consistency model, we propose a novel time-efficiency method named Consistency Policy with Q-Learning (CPQL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.06343","kind":"arxiv","version":2},"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/2310.06343/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":"2310.06343","created_at":"2026-07-05T07:36:55.133289+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.06343v2","created_at":"2026-07-05T07:36:55.133289+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.06343","created_at":"2026-07-05T07:36:55.133289+00:00"},{"alias_kind":"pith_short_12","alias_value":"6N5IGTYCSLLT","created_at":"2026-07-05T07:36:55.133289+00:00"},{"alias_kind":"pith_short_16","alias_value":"6N5IGTYCSLLTHDCS","created_at":"2026-07-05T07:36:55.133289+00:00"},{"alias_kind":"pith_short_8","alias_value":"6N5IGTYC","created_at":"2026-07-05T07:36:55.133289+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11569","citing_title":"ConsistencyPlanner: Real-time Planning with Fast-Sampling Consistency Models","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2510.03508","citing_title":"D2 Actor Critic: Diffusion Actor Meets Distributional Critic","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16054","citing_title":"Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making","ref_index":276,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16520","citing_title":"Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6N5IGTYCSLLTHDCSY5SX756QQO","json":"https://pith.science/pith/6N5IGTYCSLLTHDCSY5SX756QQO.json","graph_json":"https://pith.science/api/pith-number/6N5IGTYCSLLTHDCSY5SX756QQO/graph.json","events_json":"https://pith.science/api/pith-number/6N5IGTYCSLLTHDCSY5SX756QQO/events.json","paper":"https://pith.science/paper/6N5IGTYC"},"agent_actions":{"view_html":"https://pith.science/pith/6N5IGTYCSLLTHDCSY5SX756QQO","download_json":"https://pith.science/pith/6N5IGTYCSLLTHDCSY5SX756QQO.json","view_paper":"https://pith.science/paper/6N5IGTYC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.06343&json=true","fetch_graph":"https://pith.science/api/pith-number/6N5IGTYCSLLTHDCSY5SX756QQO/graph.json","fetch_events":"https://pith.science/api/pith-number/6N5IGTYCSLLTHDCSY5SX756QQO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6N5IGTYCSLLTHDCSY5SX756QQO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6N5IGTYCSLLTHDCSY5SX756QQO/action/storage_attestation","attest_author":"https://pith.science/pith/6N5IGTYCSLLTHDCSY5SX756QQO/action/author_attestation","sign_citation":"https://pith.science/pith/6N5IGTYCSLLTHDCSY5SX756QQO/action/citation_signature","submit_replication":"https://pith.science/pith/6N5IGTYCSLLTHDCSY5SX756QQO/action/replication_record"}},"created_at":"2026-07-05T07:36:55.133289+00:00","updated_at":"2026-07-05T07:36:55.133289+00:00"}