{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RSTF4DU4DTHAYSPF6A5HTNB2VW","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":"4a846b4993bac838a49268f27f14ded96000d0e25cbdbac3c7dda3e81e252bf7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-02T22:00:50Z","title_canon_sha256":"88ed5f64903016fe11c329c6082b873b1735935a13441df86fbc8e3f3ebd79ca"},"schema_version":"1.0","source":{"id":"2409.01477","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.01477","created_at":"2026-07-05T10:11:23Z"},{"alias_kind":"arxiv_version","alias_value":"2409.01477v2","created_at":"2026-07-05T10:11:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01477","created_at":"2026-07-05T10:11:23Z"},{"alias_kind":"pith_short_12","alias_value":"RSTF4DU4DTHA","created_at":"2026-07-05T10:11:23Z"},{"alias_kind":"pith_short_16","alias_value":"RSTF4DU4DTHAYSPF","created_at":"2026-07-05T10:11:23Z"},{"alias_kind":"pith_short_8","alias_value":"RSTF4DU4","created_at":"2026-07-05T10:11:23Z"}],"graph_snapshots":[{"event_id":"sha256:577ca52d92408db72c162ba8a60515b447b6f76036a47df45103de7a40c26678","target":"graph","created_at":"2026-07-05T10:11:23Z","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/2409.01477/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deterministic policy gradient algorithms are foundational for actor-critic methods in controlling continuous systems, yet they often encounter inaccuracies due to their dependence on the derivative of the critic's value estimates with respect to input actions. This reliance requires precise action-value gradient computations, a task that proves challenging under function approximation. We introduce an actor-critic algorithm that bypasses the need for such precision by employing a zeroth-order approximation of the action-value gradient through two-point stochastic gradient estimation within the","authors_text":"Baturay Saglam, Dionysis Kalogerias","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-02T22:00:50Z","title":"Compatible Gradient Approximations for Actor-Critic Algorithms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.01477","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":"sha256:387ef4ca22693fffbbd6c77f166e9f6da7d79bc0dbf1fa5f0cca12d96cd39202","target":"record","created_at":"2026-07-05T10:11:23Z","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":"4a846b4993bac838a49268f27f14ded96000d0e25cbdbac3c7dda3e81e252bf7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-02T22:00:50Z","title_canon_sha256":"88ed5f64903016fe11c329c6082b873b1735935a13441df86fbc8e3f3ebd79ca"},"schema_version":"1.0","source":{"id":"2409.01477","kind":"arxiv","version":2}},"canonical_sha256":"8ca65e0e9c1cce0c49e5f03a79b43aad89764591486195f3d5c5a775b5bfc67e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ca65e0e9c1cce0c49e5f03a79b43aad89764591486195f3d5c5a775b5bfc67e","first_computed_at":"2026-07-05T10:11:23.627073Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:11:23.627073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oT1/x2HGZM3EZ/DsnwPgtYcdyNRG04FW3k9sHVO69SkMs02Q3alVJ9Pxj+TynfSptLCByL11Ojq3t+6NxcXFBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:11:23.627666Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.01477","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:387ef4ca22693fffbbd6c77f166e9f6da7d79bc0dbf1fa5f0cca12d96cd39202","sha256:577ca52d92408db72c162ba8a60515b447b6f76036a47df45103de7a40c26678"],"state_sha256":"3d2f3209ac5909c122e0407e454d6c78ff1e6ed6d77e04b0746c39812ffaf301"}