{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3E4SWZW7C3NUOF4FEISKK44H6S","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":"8ff41d85a937ae9bc4172b61af7069a3eab4e21cc813bec80afbcc4fa14f144b","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-19T14:11:04Z","title_canon_sha256":"f0d16af837ffc7fd8ec6f49141dfea5b34b3ba50feffaf635ea5684f4ee3dc61"},"schema_version":"1.0","source":{"id":"2408.10015","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.10015","created_at":"2026-07-05T10:44:15Z"},{"alias_kind":"arxiv_version","alias_value":"2408.10015v2","created_at":"2026-07-05T10:44:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10015","created_at":"2026-07-05T10:44:15Z"},{"alias_kind":"pith_short_12","alias_value":"3E4SWZW7C3NU","created_at":"2026-07-05T10:44:15Z"},{"alias_kind":"pith_short_16","alias_value":"3E4SWZW7C3NUOF4F","created_at":"2026-07-05T10:44:15Z"},{"alias_kind":"pith_short_8","alias_value":"3E4SWZW7","created_at":"2026-07-05T10:44:15Z"}],"graph_snapshots":[{"event_id":"sha256:d6ec4c7407206b1ab9f1e2393fe09721d3630084fd686b6699ff6f890bf496c8","target":"graph","created_at":"2026-07-05T10:44:15Z","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/2408.10015/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the problem of computing deterministic optimal policies for constrained Markov decision processes (MDPs) with continuous state and action spaces, which are widely encountered in constrained dynamical systems. Designing deterministic policy gradient methods in continuous state and action spaces is particularly challenging due to the lack of enumerable state-action pairs and the adoption of deterministic policies, hindering the application of existing policy gradient methods. To this end, we develop a deterministic policy gradient primal-dual method to find an optimal deterministic poli","authors_text":"Alejandro Ribeiro, Antonio G. Marques, Dongsheng Ding, Sergio Rozada","cross_cats":["math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-19T14:11:04Z","title":"Deterministic Policy Gradient Primal-Dual Methods for Continuous-Space Constrained MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10015","kind":"arxiv","version":2},"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":"sha256:3bb2b98cd9986ae3ad3b9a9912ad7c5c5292f44d0b61cdaee8c6588eaa481012","target":"record","created_at":"2026-07-05T10:44:15Z","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":"8ff41d85a937ae9bc4172b61af7069a3eab4e21cc813bec80afbcc4fa14f144b","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-19T14:11:04Z","title_canon_sha256":"f0d16af837ffc7fd8ec6f49141dfea5b34b3ba50feffaf635ea5684f4ee3dc61"},"schema_version":"1.0","source":{"id":"2408.10015","kind":"arxiv","version":2}},"canonical_sha256":"d9392b66df16db4717852224a57387f4a335d4013e66528345c815c6739e409b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d9392b66df16db4717852224a57387f4a335d4013e66528345c815c6739e409b","first_computed_at":"2026-07-05T10:44:15.561410Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:44:15.561410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dcQ1U+NjMHilslffauF51gJbrd/U94GPy/DSilp1u3U/S74YeF01S0/WLwmebJoP+M/H0KzltWfsrq61Ji8eDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:44:15.562030Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.10015","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3bb2b98cd9986ae3ad3b9a9912ad7c5c5292f44d0b61cdaee8c6588eaa481012","sha256:d6ec4c7407206b1ab9f1e2393fe09721d3630084fd686b6699ff6f890bf496c8"],"state_sha256":"3648f600e2c10c3498d263f1d5cebf363049123ca1138fa5a0deb0bfceb51563"}