{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TJBDUYOH4LS2SL3XGAZSYK4K5H","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"072d2aefb7769baee7ee92a4049f85b3521687075b1bdf69e83a5944900c989d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-24T03:23:27Z","title_canon_sha256":"4355f7c42d5a0ced9c4e88ae9f72201009b84e61cd0890bb1cc7b14dc40a30a5"},"schema_version":"1.0","source":{"id":"2405.15177","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.15177","created_at":"2026-07-05T09:52:38Z"},{"alias_kind":"arxiv_version","alias_value":"2405.15177v5","created_at":"2026-07-05T09:52:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15177","created_at":"2026-07-05T09:52:38Z"},{"alias_kind":"pith_short_12","alias_value":"TJBDUYOH4LS2","created_at":"2026-07-05T09:52:38Z"},{"alias_kind":"pith_short_16","alias_value":"TJBDUYOH4LS2SL3X","created_at":"2026-07-05T09:52:38Z"},{"alias_kind":"pith_short_8","alias_value":"TJBDUYOH","created_at":"2026-07-05T09:52:38Z"}],"graph_snapshots":[{"event_id":"sha256:2381c502261a88fab4c3612b7af76143db8bbb955561aa7dc812e72e55d015ce","target":"graph","created_at":"2026-07-05T09:52:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2405.15177/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-24T03:23:27Z","title":"Diffusion Actor-Critic with Entropy Regulator"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15177","kind":"arxiv","version":5},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:80e21f4790423ac53b757de3e64b6fed654f749a00552f1d3a0fd7c622b0ac4f","target":"record","created_at":"2026-07-05T09:52:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"072d2aefb7769baee7ee92a4049f85b3521687075b1bdf69e83a5944900c989d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-24T03:23:27Z","title_canon_sha256":"4355f7c42d5a0ced9c4e88ae9f72201009b84e61cd0890bb1cc7b14dc40a30a5"},"schema_version":"1.0","source":{"id":"2405.15177","kind":"arxiv","version":5}},"canonical_sha256":"9a423a61c7e2e5a92f7730332c2b8ae9f1043daba91a8123045c52741e47c891","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a423a61c7e2e5a92f7730332c2b8ae9f1043daba91a8123045c52741e47c891","first_computed_at":"2026-07-05T09:52:38.270836Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:52:38.270836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a+i0PG4L703+CeQ37JBWWx09HefK0Fq1VCqtsbAD8VqtScB9ilU9DZ4MXluHqI3ENh/fhm6ejA5lFRKVTJIDCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:52:38.271301Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.15177","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80e21f4790423ac53b757de3e64b6fed654f749a00552f1d3a0fd7c622b0ac4f","sha256:2381c502261a88fab4c3612b7af76143db8bbb955561aa7dc812e72e55d015ce"],"state_sha256":"3b1423609a8d531be65d62bbdccde918b0473fe2053ef144f769523f8297576e"}