{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:SOP7XMBFMBQWSJIE2PER7C3QT5","short_pith_number":"pith:SOP7XMBF","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"},"canonical_sha256":"939ffbb0256061692504d3c91f8b709f4ee937f881a9f594ed30cecaa89431e9","source":{"kind":"arxiv","id":"1905.01576","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.01576","created_at":"2026-05-17T23:46:58Z"},{"alias_kind":"arxiv_version","alias_value":"1905.01576v1","created_at":"2026-05-17T23:46:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.01576","created_at":"2026-05-17T23:46:58Z"},{"alias_kind":"pith_short_12","alias_value":"SOP7XMBFMBQW","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SOP7XMBFMBQWSJIE","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SOP7XMBF","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:SOP7XMBFMBQWSJIE2PER7C3QT5","target":"record","payload":{"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"},"canonical_sha256":"939ffbb0256061692504d3c91f8b709f4ee937f881a9f594ed30cecaa89431e9","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"},"source_kind":"arxiv","source_id":"1905.01576","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:46:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JvohLJGIteA5YQgsogJ62vhUJqeaC2+6+CoDitcGNu3J7LBX1K3kFOFwTE21yPRn++KbHR+PSXRXKmAw0V9QDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T22:23:24.589032Z"},"content_sha256":"f0a37c18baa362126b540fbd0808a603a9ad98913ed19bd5a7ed632991eefb8b","schema_version":"1.0","event_id":"sha256:f0a37c18baa362126b540fbd0808a603a9ad98913ed19bd5a7ed632991eefb8b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:SOP7XMBFMBQWSJIE2PER7C3QT5","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:46:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XlNcDh6L306+IVsqjzgPOSwl4FYovZhRMJsOoeHj6t6LgIyMe+e7dVKlhD20IbX9hnWpDQDqXGcMtWcD+KgGBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T22:23:24.589653Z"},"content_sha256":"2d19926253256fc5299bc618216543d316e928a1e6c82c1830f1ef58f71683d6","schema_version":"1.0","event_id":"sha256:2d19926253256fc5299bc618216543d316e928a1e6c82c1830f1ef58f71683d6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SOP7XMBFMBQWSJIE2PER7C3QT5/bundle.json","state_url":"https://pith.science/pith/SOP7XMBFMBQWSJIE2PER7C3QT5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SOP7XMBFMBQWSJIE2PER7C3QT5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-30T22:23:24Z","links":{"resolver":"https://pith.science/pith/SOP7XMBFMBQWSJIE2PER7C3QT5","bundle":"https://pith.science/pith/SOP7XMBFMBQWSJIE2PER7C3QT5/bundle.json","state":"https://pith.science/pith/SOP7XMBFMBQWSJIE2PER7C3QT5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SOP7XMBFMBQWSJIE2PER7C3QT5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:SOP7XMBFMBQWSJIE2PER7C3QT5","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":"078f479b63bfda65aa3fee4f5fa4d2ade93ab86f5a7f273404104c6bf60df16d","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-05T01:42:44Z","title_canon_sha256":"9d98b08e9c644931f2c7e56afa698f24fdc4a2b1924a3141fe2ada3b6abde021"},"schema_version":"1.0","source":{"id":"1905.01576","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.01576","created_at":"2026-05-17T23:46:58Z"},{"alias_kind":"arxiv_version","alias_value":"1905.01576v1","created_at":"2026-05-17T23:46:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.01576","created_at":"2026-05-17T23:46:58Z"},{"alias_kind":"pith_short_12","alias_value":"SOP7XMBFMBQW","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SOP7XMBFMBQWSJIE","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SOP7XMBF","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:2d19926253256fc5299bc618216543d316e928a1e6c82c1830f1ef58f71683d6","target":"graph","created_at":"2026-05-17T23:46:58Z","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"},"paper":{"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}}) $ ","authors_text":"Chengzhuo Ni, Lin F. Yang, Mengdi Wang","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-05T01:42:44Z","title":"Learning to Control in Metric Space with Optimal Regret"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.01576","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:f0a37c18baa362126b540fbd0808a603a9ad98913ed19bd5a7ed632991eefb8b","target":"record","created_at":"2026-05-17T23:46:58Z","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":"078f479b63bfda65aa3fee4f5fa4d2ade93ab86f5a7f273404104c6bf60df16d","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-05T01:42:44Z","title_canon_sha256":"9d98b08e9c644931f2c7e56afa698f24fdc4a2b1924a3141fe2ada3b6abde021"},"schema_version":"1.0","source":{"id":"1905.01576","kind":"arxiv","version":1}},"canonical_sha256":"939ffbb0256061692504d3c91f8b709f4ee937f881a9f594ed30cecaa89431e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"939ffbb0256061692504d3c91f8b709f4ee937f881a9f594ed30cecaa89431e9","first_computed_at":"2026-05-17T23:46:58.107892Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:58.107892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"91CH6s4zco7XohWG++GpWJuqEG1AaCCWxGHmftKFTzfbyKYpmgplMqVi4tVLP6BZXMEjn6NW6WXK69q8E4VeCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:58.108441Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.01576","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0a37c18baa362126b540fbd0808a603a9ad98913ed19bd5a7ed632991eefb8b","sha256:2d19926253256fc5299bc618216543d316e928a1e6c82c1830f1ef58f71683d6"],"state_sha256":"ff2c0b0d53e9e83ab0aec1f21bab6fb5c4ed55e53bfef4a5c8085f5f4cebb251"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dNuTUl3IojG6kXCtClXdh0y/vVX3qhZ/tubjjtlyxVt3c+KRIDt3RLpyb77j/PVHbKVBw5rR1cS67ODO8Qj2Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T22:23:24.593235Z","bundle_sha256":"81259caa7b24f5183f710403cb3be70198d15c5844fe8c5deea6ba84d34ffa8e"}}