{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:AOBZGN43BBIXHVGKYNHV7KYBNC","short_pith_number":"pith:AOBZGN43","schema_version":"1.0","canonical_sha256":"038393379b085173d4cac34f5fab0168be208a6847b308bd265ba3a432820d8a","source":{"kind":"arxiv","id":"1906.11245","version":1},"attestation_state":"computed","paper":{"title":"A Tractable Algorithm For Finite-Horizon Continuous Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Lakshmanan Kailasam, Phanideep Gampa, Sairam Satwik Kondamudi","submitted_at":"2019-06-26T09:11:14Z","abstract_excerpt":"We consider the finite horizon continuous reinforcement learning problem. Our contribution is three-fold. First,we give a tractable algorithm based on optimistic value iteration for the problem. Next,we give a lower bound on regret of order $\\Omega(T^{2/3})$ for any algorithm discretizes the state space, improving the previous regret bound of $\\Omega(T^{1/2})$ of Ortner and Ryabko \\cite{contrl} for the same problem. Next,under the assumption that the rewards and transitions are H\\\"{o}lder Continuous we show that the upper bound on the discretization error is $const.Ln^{-\\alpha}T$. Finally,we g"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1906.11245","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-26T09:11:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1ff6fdcd80af0bb53533ba92df56ff070102136e357cf0b2e75f20980a324501","abstract_canon_sha256":"f6dcda80c04dc2f113f4fff1a7519b9b9ae976ace1b0cd0d78665b2eae30a415"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:51:05.466542Z","signature_b64":"KJQ+cqyZnsjolCDidE1Q8Edrzi/lYOhwlzOmVYfPpvJuE/pPMXbHdhLjvLdSwdSu2VQWzg3+Ti6j/wQQbfwkCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"038393379b085173d4cac34f5fab0168be208a6847b308bd265ba3a432820d8a","last_reissued_at":"2026-07-04T23:51:05.466121Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:51:05.466121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Tractable Algorithm For Finite-Horizon Continuous Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Lakshmanan Kailasam, Phanideep Gampa, Sairam Satwik Kondamudi","submitted_at":"2019-06-26T09:11:14Z","abstract_excerpt":"We consider the finite horizon continuous reinforcement learning problem. Our contribution is three-fold. First,we give a tractable algorithm based on optimistic value iteration for the problem. Next,we give a lower bound on regret of order $\\Omega(T^{2/3})$ for any algorithm discretizes the state space, improving the previous regret bound of $\\Omega(T^{1/2})$ of Ortner and Ryabko \\cite{contrl} for the same problem. Next,under the assumption that the rewards and transitions are H\\\"{o}lder Continuous we show that the upper bound on the discretization error is $const.Ln^{-\\alpha}T$. Finally,we g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.11245","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1906.11245/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1906.11245","created_at":"2026-07-04T23:51:05.466182+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.11245v1","created_at":"2026-07-04T23:51:05.466182+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.11245","created_at":"2026-07-04T23:51:05.466182+00:00"},{"alias_kind":"pith_short_12","alias_value":"AOBZGN43BBIX","created_at":"2026-07-04T23:51:05.466182+00:00"},{"alias_kind":"pith_short_16","alias_value":"AOBZGN43BBIXHVGK","created_at":"2026-07-04T23:51:05.466182+00:00"},{"alias_kind":"pith_short_8","alias_value":"AOBZGN43","created_at":"2026-07-04T23:51:05.466182+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AOBZGN43BBIXHVGKYNHV7KYBNC","json":"https://pith.science/pith/AOBZGN43BBIXHVGKYNHV7KYBNC.json","graph_json":"https://pith.science/api/pith-number/AOBZGN43BBIXHVGKYNHV7KYBNC/graph.json","events_json":"https://pith.science/api/pith-number/AOBZGN43BBIXHVGKYNHV7KYBNC/events.json","paper":"https://pith.science/paper/AOBZGN43"},"agent_actions":{"view_html":"https://pith.science/pith/AOBZGN43BBIXHVGKYNHV7KYBNC","download_json":"https://pith.science/pith/AOBZGN43BBIXHVGKYNHV7KYBNC.json","view_paper":"https://pith.science/paper/AOBZGN43","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.11245&json=true","fetch_graph":"https://pith.science/api/pith-number/AOBZGN43BBIXHVGKYNHV7KYBNC/graph.json","fetch_events":"https://pith.science/api/pith-number/AOBZGN43BBIXHVGKYNHV7KYBNC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AOBZGN43BBIXHVGKYNHV7KYBNC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AOBZGN43BBIXHVGKYNHV7KYBNC/action/storage_attestation","attest_author":"https://pith.science/pith/AOBZGN43BBIXHVGKYNHV7KYBNC/action/author_attestation","sign_citation":"https://pith.science/pith/AOBZGN43BBIXHVGKYNHV7KYBNC/action/citation_signature","submit_replication":"https://pith.science/pith/AOBZGN43BBIXHVGKYNHV7KYBNC/action/replication_record"}},"created_at":"2026-07-04T23:51:05.466182+00:00","updated_at":"2026-07-04T23:51:05.466182+00:00"}