{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:AOBZGN43BBIXHVGKYNHV7KYBNC","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":"f6dcda80c04dc2f113f4fff1a7519b9b9ae976ace1b0cd0d78665b2eae30a415","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-26T09:11:14Z","title_canon_sha256":"1ff6fdcd80af0bb53533ba92df56ff070102136e357cf0b2e75f20980a324501"},"schema_version":"1.0","source":{"id":"1906.11245","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.11245","created_at":"2026-07-04T23:51:05Z"},{"alias_kind":"arxiv_version","alias_value":"1906.11245v1","created_at":"2026-07-04T23:51:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.11245","created_at":"2026-07-04T23:51:05Z"},{"alias_kind":"pith_short_12","alias_value":"AOBZGN43BBIX","created_at":"2026-07-04T23:51:05Z"},{"alias_kind":"pith_short_16","alias_value":"AOBZGN43BBIXHVGK","created_at":"2026-07-04T23:51:05Z"},{"alias_kind":"pith_short_8","alias_value":"AOBZGN43","created_at":"2026-07-04T23:51:05Z"}],"graph_snapshots":[{"event_id":"sha256:008242c341fd66ab06edebbb938d2bdc4d955e5023e604aba9bb1caf115656b6","target":"graph","created_at":"2026-07-04T23:51:05Z","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/1906.11245/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Lakshmanan Kailasam, Phanideep Gampa, Sairam Satwik Kondamudi","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-26T09:11:14Z","title":"A Tractable Algorithm For Finite-Horizon Continuous Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.11245","kind":"arxiv","version":1},"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":"sha256:375a27189b6cef83be36893f98e84c8432d8ccf441914712460e7c101da2f993","target":"record","created_at":"2026-07-04T23:51:05Z","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":"f6dcda80c04dc2f113f4fff1a7519b9b9ae976ace1b0cd0d78665b2eae30a415","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-26T09:11:14Z","title_canon_sha256":"1ff6fdcd80af0bb53533ba92df56ff070102136e357cf0b2e75f20980a324501"},"schema_version":"1.0","source":{"id":"1906.11245","kind":"arxiv","version":1}},"canonical_sha256":"038393379b085173d4cac34f5fab0168be208a6847b308bd265ba3a432820d8a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"038393379b085173d4cac34f5fab0168be208a6847b308bd265ba3a432820d8a","first_computed_at":"2026-07-04T23:51:05.466121Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:51:05.466121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KJQ+cqyZnsjolCDidE1Q8Edrzi/lYOhwlzOmVYfPpvJuE/pPMXbHdhLjvLdSwdSu2VQWzg3+Ti6j/wQQbfwkCg==","signature_status":"signed_v1","signed_at":"2026-07-04T23:51:05.466542Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.11245","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:375a27189b6cef83be36893f98e84c8432d8ccf441914712460e7c101da2f993","sha256:008242c341fd66ab06edebbb938d2bdc4d955e5023e604aba9bb1caf115656b6"],"state_sha256":"1abfb1d09f1880933019b2df9ad4be1f30b7b7072618fd00ffcca3cf57cab73c"}