{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TJBDUYOH4LS2SL3XGAZSYK4K5H","short_pith_number":"pith:TJBDUYOH","schema_version":"1.0","canonical_sha256":"9a423a61c7e2e5a92f7730332c2b8ae9f1043daba91a8123045c52741e47c891","source":{"kind":"arxiv","id":"2405.15177","version":5},"attestation_state":"computed","paper":{"title":"Diffusion Actor-Critic with Entropy Regulator","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jiang Wu, Jingliang Duan, Likun Wang, Liming Xiao, Shengbo Eben Li, Tong Liu, Wenjun Zou, Wenxuan Wang, Xujie Song, Yinuo Wang, Yuxuan Jiang","submitted_at":"2024-05-24T03:23:27Z","abstract_excerpt":"Reinforcement learning (RL) has proven highly effective in addressing complex decision-making and control tasks. However, in most traditional RL algorithms, the policy is typically parameterized as a diagonal Gaussian distribution with learned mean and variance, which constrains their capability to acquire complex policies. In response to this problem, we propose an online RL algorithm termed diffusion actor-critic with entropy regulator (DACER). This algorithm conceptualizes the reverse process of the diffusion model as a novel policy function and leverages the capability of the diffusion mod"},"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":"2405.15177","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-24T03:23:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4355f7c42d5a0ced9c4e88ae9f72201009b84e61cd0890bb1cc7b14dc40a30a5","abstract_canon_sha256":"072d2aefb7769baee7ee92a4049f85b3521687075b1bdf69e83a5944900c989d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:38.271301Z","signature_b64":"a+i0PG4L703+CeQ37JBWWx09HefK0Fq1VCqtsbAD8VqtScB9ilU9DZ4MXluHqI3ENh/fhm6ejA5lFRKVTJIDCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a423a61c7e2e5a92f7730332c2b8ae9f1043daba91a8123045c52741e47c891","last_reissued_at":"2026-07-05T09:52:38.270836Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:38.270836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion Actor-Critic with Entropy Regulator","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jiang Wu, Jingliang Duan, Likun Wang, Liming Xiao, Shengbo Eben Li, Tong Liu, Wenjun Zou, Wenxuan Wang, Xujie Song, Yinuo Wang, Yuxuan Jiang","submitted_at":"2024-05-24T03:23:27Z","abstract_excerpt":"Reinforcement learning (RL) has proven highly effective in addressing complex decision-making and control tasks. However, in most traditional RL algorithms, the policy is typically parameterized as a diagonal Gaussian distribution with learned mean and variance, which constrains their capability to acquire complex policies. In response to this problem, we propose an online RL algorithm termed diffusion actor-critic with entropy regulator (DACER). This algorithm conceptualizes the reverse process of the diffusion model as a novel policy function and leverages the capability of the diffusion mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15177","kind":"arxiv","version":5},"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/2405.15177/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":"2405.15177","created_at":"2026-07-05T09:52:38.270894+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.15177v5","created_at":"2026-07-05T09:52:38.270894+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15177","created_at":"2026-07-05T09:52:38.270894+00:00"},{"alias_kind":"pith_short_12","alias_value":"TJBDUYOH4LS2","created_at":"2026-07-05T09:52:38.270894+00:00"},{"alias_kind":"pith_short_16","alias_value":"TJBDUYOH4LS2SL3X","created_at":"2026-07-05T09:52:38.270894+00:00"},{"alias_kind":"pith_short_8","alias_value":"TJBDUYOH","created_at":"2026-07-05T09:52:38.270894+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16520","citing_title":"Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing","ref_index":210,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TJBDUYOH4LS2SL3XGAZSYK4K5H","json":"https://pith.science/pith/TJBDUYOH4LS2SL3XGAZSYK4K5H.json","graph_json":"https://pith.science/api/pith-number/TJBDUYOH4LS2SL3XGAZSYK4K5H/graph.json","events_json":"https://pith.science/api/pith-number/TJBDUYOH4LS2SL3XGAZSYK4K5H/events.json","paper":"https://pith.science/paper/TJBDUYOH"},"agent_actions":{"view_html":"https://pith.science/pith/TJBDUYOH4LS2SL3XGAZSYK4K5H","download_json":"https://pith.science/pith/TJBDUYOH4LS2SL3XGAZSYK4K5H.json","view_paper":"https://pith.science/paper/TJBDUYOH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.15177&json=true","fetch_graph":"https://pith.science/api/pith-number/TJBDUYOH4LS2SL3XGAZSYK4K5H/graph.json","fetch_events":"https://pith.science/api/pith-number/TJBDUYOH4LS2SL3XGAZSYK4K5H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TJBDUYOH4LS2SL3XGAZSYK4K5H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TJBDUYOH4LS2SL3XGAZSYK4K5H/action/storage_attestation","attest_author":"https://pith.science/pith/TJBDUYOH4LS2SL3XGAZSYK4K5H/action/author_attestation","sign_citation":"https://pith.science/pith/TJBDUYOH4LS2SL3XGAZSYK4K5H/action/citation_signature","submit_replication":"https://pith.science/pith/TJBDUYOH4LS2SL3XGAZSYK4K5H/action/replication_record"}},"created_at":"2026-07-05T09:52:38.270894+00:00","updated_at":"2026-07-05T09:52:38.270894+00:00"}