{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:LYVO6TMHHNPHYBQLZILDYM55VB","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":"78573736f9010a5be6be4dfd0fe865236ea5688dd04f0c682d031f0e4d0d8488","cross_cats_sorted":["cs.LG","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2019-04-25T18:57:49Z","title_canon_sha256":"15c6531e0af9bda819d3a738bc5a008607c250a26a56e8edce1b31c5afd51902"},"schema_version":"1.0","source":{"id":"1904.11538","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.11538","created_at":"2026-06-04T20:14:27Z"},{"alias_kind":"arxiv_version","alias_value":"1904.11538v3","created_at":"2026-06-04T20:14:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.11538","created_at":"2026-06-04T20:14:27Z"},{"alias_kind":"pith_short_12","alias_value":"LYVO6TMHHNPH","created_at":"2026-06-04T20:14:27Z"},{"alias_kind":"pith_short_16","alias_value":"LYVO6TMHHNPHYBQL","created_at":"2026-06-04T20:14:27Z"},{"alias_kind":"pith_short_8","alias_value":"LYVO6TMH","created_at":"2026-06-04T20:14:27Z"}],"graph_snapshots":[{"event_id":"sha256:83cea372b12adf005d84b25c27ae8a0879308649c96672047e6157e5dfc295d4","target":"graph","created_at":"2026-06-04T20:14:27Z","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/1904.11538/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The objective in this paper is to obtain fast converging reinforcement learning algorithms to approximate solutions to the problem of discounted cost optimal stopping in an irreducible, uniformly ergodic Markov chain, evolving on a compact subset of $\\mathbb{R}^n$. We build on the dynamic programming approach taken by Tsitsikilis and Van Roy, wherein they propose a Q-learning algorithm to estimate the optimal state-action value function, which then defines an optimal stopping rule. We provide insights as to why the convergence rate of this algorithm can be slow, and propose a fast-converging a","authors_text":"Adithya M. Devraj, Ana Bu\\v{s}i\\'c, Sean P. Meyn, Shuhang Chen","cross_cats":["cs.LG","cs.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2019-04-25T18:57:49Z","title":"Zap Q-Learning for Optimal Stopping Time Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.11538","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":"sha256:885bd13cfe6345d8e3b52ab51e89b73987edce25a92924773124ca257073d5de","target":"record","created_at":"2026-06-04T20:14:27Z","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":"78573736f9010a5be6be4dfd0fe865236ea5688dd04f0c682d031f0e4d0d8488","cross_cats_sorted":["cs.LG","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2019-04-25T18:57:49Z","title_canon_sha256":"15c6531e0af9bda819d3a738bc5a008607c250a26a56e8edce1b31c5afd51902"},"schema_version":"1.0","source":{"id":"1904.11538","kind":"arxiv","version":3}},"canonical_sha256":"5e2aef4d873b5e7c060bca163c33bda870835bdb30b123822cc3f62a11b11af3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e2aef4d873b5e7c060bca163c33bda870835bdb30b123822cc3f62a11b11af3","first_computed_at":"2026-06-04T20:14:27.433287Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T20:14:27.433287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"91TmXXzAGHXcz8FegbKAuRiS7B/wiUA3YE742dOyWiLvDe/lyPiqzEzi+ENOx5RUactR0KGXE5mA1pTzNj3+Cg==","signature_status":"signed_v1","signed_at":"2026-06-04T20:14:27.433847Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.11538","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:885bd13cfe6345d8e3b52ab51e89b73987edce25a92924773124ca257073d5de","sha256:83cea372b12adf005d84b25c27ae8a0879308649c96672047e6157e5dfc295d4"],"state_sha256":"945839d6605c12c48d5ef333687bb6838d5fb436be3a7745fb8d1698cefe32f1"}