{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:SOP7XMBFMBQWSJIE2PER7C3QT5","short_pith_number":"pith:SOP7XMBF","schema_version":"1.0","canonical_sha256":"939ffbb0256061692504d3c91f8b709f4ee937f881a9f594ed30cecaa89431e9","source":{"kind":"arxiv","id":"1905.01576","version":1},"attestation_state":"computed","paper":{"title":"Learning to Control in Metric Space with Optimal Regret","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chengzhuo Ni, Lin F. Yang, Mengdi Wang","submitted_at":"2019-05-05T01:42:44Z","abstract_excerpt":"We study online reinforcement learning for finite-horizon deterministic control systems with {\\it arbitrary} state and action spaces. Suppose that the transition dynamics and reward function is unknown, but the state and action space is endowed with a metric that characterizes the proximity between different states and actions. We provide a surprisingly simple upper-confidence reinforcement learning algorithm that uses a function approximation oracle to estimate optimistic Q functions from experiences. We show that the regret of the algorithm after $K$ episodes is $O(HL(KH)^{\\frac{d-1}{d}}) $ "},"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":"1905.01576","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-05T01:42:44Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"9d98b08e9c644931f2c7e56afa698f24fdc4a2b1924a3141fe2ada3b6abde021","abstract_canon_sha256":"078f479b63bfda65aa3fee4f5fa4d2ade93ab86f5a7f273404104c6bf60df16d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:58.108441Z","signature_b64":"91CH6s4zco7XohWG++GpWJuqEG1AaCCWxGHmftKFTzfbyKYpmgplMqVi4tVLP6BZXMEjn6NW6WXK69q8E4VeCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"939ffbb0256061692504d3c91f8b709f4ee937f881a9f594ed30cecaa89431e9","last_reissued_at":"2026-05-17T23:46:58.107892Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:58.107892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Control in Metric Space with Optimal Regret","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chengzhuo Ni, Lin F. Yang, Mengdi Wang","submitted_at":"2019-05-05T01:42:44Z","abstract_excerpt":"We study online reinforcement learning for finite-horizon deterministic control systems with {\\it arbitrary} state and action spaces. Suppose that the transition dynamics and reward function is unknown, but the state and action space is endowed with a metric that characterizes the proximity between different states and actions. We provide a surprisingly simple upper-confidence reinforcement learning algorithm that uses a function approximation oracle to estimate optimistic Q functions from experiences. We show that the regret of the algorithm after $K$ episodes is $O(HL(KH)^{\\frac{d-1}{d}}) $ "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.01576","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":""},"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":"1905.01576","created_at":"2026-05-17T23:46:58.107982+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.01576v1","created_at":"2026-05-17T23:46:58.107982+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.01576","created_at":"2026-05-17T23:46:58.107982+00:00"},{"alias_kind":"pith_short_12","alias_value":"SOP7XMBFMBQW","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"SOP7XMBFMBQWSJIE","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"SOP7XMBF","created_at":"2026-05-18T12:33:27.125529+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/SOP7XMBFMBQWSJIE2PER7C3QT5","json":"https://pith.science/pith/SOP7XMBFMBQWSJIE2PER7C3QT5.json","graph_json":"https://pith.science/api/pith-number/SOP7XMBFMBQWSJIE2PER7C3QT5/graph.json","events_json":"https://pith.science/api/pith-number/SOP7XMBFMBQWSJIE2PER7C3QT5/events.json","paper":"https://pith.science/paper/SOP7XMBF"},"agent_actions":{"view_html":"https://pith.science/pith/SOP7XMBFMBQWSJIE2PER7C3QT5","download_json":"https://pith.science/pith/SOP7XMBFMBQWSJIE2PER7C3QT5.json","view_paper":"https://pith.science/paper/SOP7XMBF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.01576&json=true","fetch_graph":"https://pith.science/api/pith-number/SOP7XMBFMBQWSJIE2PER7C3QT5/graph.json","fetch_events":"https://pith.science/api/pith-number/SOP7XMBFMBQWSJIE2PER7C3QT5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SOP7XMBFMBQWSJIE2PER7C3QT5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SOP7XMBFMBQWSJIE2PER7C3QT5/action/storage_attestation","attest_author":"https://pith.science/pith/SOP7XMBFMBQWSJIE2PER7C3QT5/action/author_attestation","sign_citation":"https://pith.science/pith/SOP7XMBFMBQWSJIE2PER7C3QT5/action/citation_signature","submit_replication":"https://pith.science/pith/SOP7XMBFMBQWSJIE2PER7C3QT5/action/replication_record"}},"created_at":"2026-05-17T23:46:58.107982+00:00","updated_at":"2026-05-17T23:46:58.107982+00:00"}