{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:BGXSPP6BCBWHW6WPEATPUJNR6E","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":"b4f2f36757399f51d227c0274df1abf6be6d158ddf79f54d4cf3e29ca595368c","cross_cats_sorted":["cs.SY","eess.SY","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-28T18:05:21Z","title_canon_sha256":"bd5397b84136f7e54690fc62d205152c9d676d12615898e78df82acf8f6ef7e9"},"schema_version":"1.0","source":{"id":"1812.11137","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.11137","created_at":"2026-06-04T20:13:50Z"},{"alias_kind":"arxiv_version","alias_value":"1812.11137v2","created_at":"2026-06-04T20:13:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.11137","created_at":"2026-06-04T20:13:50Z"},{"alias_kind":"pith_short_12","alias_value":"BGXSPP6BCBWH","created_at":"2026-06-04T20:13:50Z"},{"alias_kind":"pith_short_16","alias_value":"BGXSPP6BCBWHW6WP","created_at":"2026-06-04T20:13:50Z"},{"alias_kind":"pith_short_8","alias_value":"BGXSPP6B","created_at":"2026-06-04T20:13:50Z"}],"graph_snapshots":[{"event_id":"sha256:64877462584c9fb8e5df10aa04715e9ccdbc00ab5f8e6f0eece22a8324c723e4","target":"graph","created_at":"2026-06-04T20:13:50Z","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/1812.11137/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Value functions derived from Markov decision processes arise as a central component of algorithms as well as performance metrics in many statistics and engineering applications of machine learning techniques. Computation of the solution to the associated Bellman equations is challenging in most practical cases of interest. A popular class of approximation techniques, known as Temporal Difference (TD) learning algorithms, are an important sub-class of general reinforcement learning methods. The algorithms introduced in this paper are intended to resolve two well-known difficulties of TD-learnin","authors_text":"Adithya M. Devraj, Ioannis Kontoyiannis, Sean P. Meyn","cross_cats":["cs.SY","eess.SY","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-28T18:05:21Z","title":"Differential Temporal Difference Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.11137","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:f77346d6ea8c4f2a2d3fd9687e7ec8b5752485320a51305f1c10c45c7c78efb0","target":"record","created_at":"2026-06-04T20:13:50Z","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":"b4f2f36757399f51d227c0274df1abf6be6d158ddf79f54d4cf3e29ca595368c","cross_cats_sorted":["cs.SY","eess.SY","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-28T18:05:21Z","title_canon_sha256":"bd5397b84136f7e54690fc62d205152c9d676d12615898e78df82acf8f6ef7e9"},"schema_version":"1.0","source":{"id":"1812.11137","kind":"arxiv","version":2}},"canonical_sha256":"09af27bfc1106c7b7acf2026fa25b1f13ba114254aa0f7c60917441e4639b13a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"09af27bfc1106c7b7acf2026fa25b1f13ba114254aa0f7c60917441e4639b13a","first_computed_at":"2026-06-04T20:13:50.724930Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T20:13:50.724930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eh5n2odP74Y3FSjlt/v4oIIRmaXh5l5+giaWCupf1j2wzh+NNT89BKpyTgRdKBALoBP3XU412ss7mFyIMXAVBg==","signature_status":"signed_v1","signed_at":"2026-06-04T20:13:50.725472Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.11137","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f77346d6ea8c4f2a2d3fd9687e7ec8b5752485320a51305f1c10c45c7c78efb0","sha256:64877462584c9fb8e5df10aa04715e9ccdbc00ab5f8e6f0eece22a8324c723e4"],"state_sha256":"3e44eee6cd0cb93557322b537794b7bbc785dea844b2abfcfe538c9641d41ed6"}