{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EQ46P5IJYEMXVM2KZVAZTFXL7B","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":"877b3c6c95e691d696fc19c1b5ffd7a7712a94961c058dd5b22bdadfa15bdc48","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T15:34:30Z","title_canon_sha256":"0bdb3697c2f9832a9da9815eac6325cc1ca198f3aa052603be659ab8eb73f323"},"schema_version":"1.0","source":{"id":"2402.04080","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.04080","created_at":"2026-07-05T09:58:18Z"},{"alias_kind":"arxiv_version","alias_value":"2402.04080v3","created_at":"2026-07-05T09:58:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04080","created_at":"2026-07-05T09:58:18Z"},{"alias_kind":"pith_short_12","alias_value":"EQ46P5IJYEMX","created_at":"2026-07-05T09:58:18Z"},{"alias_kind":"pith_short_16","alias_value":"EQ46P5IJYEMXVM2K","created_at":"2026-07-05T09:58:18Z"},{"alias_kind":"pith_short_8","alias_value":"EQ46P5IJ","created_at":"2026-07-05T09:58:18Z"}],"graph_snapshots":[{"event_id":"sha256:d8cadd9a6201e1c123cc1afeaaf17a5a04a5d1561b005d6086dd26c00dcbb026","target":"graph","created_at":"2026-07-05T09:58:18Z","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/2402.04080/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents advanced techniques of training diffusion policies for offline reinforcement learning (RL). At the core is a mean-reverting stochastic differential equation (SDE) that transfers a complex action distribution into a standard Gaussian and then samples actions conditioned on the environment state with a corresponding reverse-time SDE, like a typical diffusion policy. We show that such an SDE has a solution that we can use to calculate the log probability of the policy, yielding an entropy regularizer that improves the exploration of offline datasets. To mitigate the impact of ","authors_text":"Jens Sj\\\"olund, Per Mattsson, Ruoqi Zhang, Thomas B. Sch\\\"on, Ziwei Luo","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T15:34:30Z","title":"Entropy-regularized Diffusion Policy with Q-Ensembles for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04080","kind":"arxiv","version":3},"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":"sha256:70a5554cc1f999c9ff5405d1c4a24f293b63412a72c1730493de2f72c37a2705","target":"record","created_at":"2026-07-05T09:58:18Z","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":"877b3c6c95e691d696fc19c1b5ffd7a7712a94961c058dd5b22bdadfa15bdc48","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T15:34:30Z","title_canon_sha256":"0bdb3697c2f9832a9da9815eac6325cc1ca198f3aa052603be659ab8eb73f323"},"schema_version":"1.0","source":{"id":"2402.04080","kind":"arxiv","version":3}},"canonical_sha256":"2439e7f509c1197ab34acd419996ebf862935ab2cb91d80431f43b7c087dc2d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2439e7f509c1197ab34acd419996ebf862935ab2cb91d80431f43b7c087dc2d3","first_computed_at":"2026-07-05T09:58:18.792569Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:58:18.792569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yJqby+uWQ4o/zUkFUJ9AUbGR8WKJ4IE+o7gbclMsO1F5t1wxVcIihru7w7TH7pWsZUOcqx1a6uAANkJozq0rCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:58:18.792999Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.04080","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70a5554cc1f999c9ff5405d1c4a24f293b63412a72c1730493de2f72c37a2705","sha256:d8cadd9a6201e1c123cc1afeaaf17a5a04a5d1561b005d6086dd26c00dcbb026"],"state_sha256":"10d3918a56fa6910fae2098d1b6bd526ba0d35f086cfb347e1831e51a64808c6"}