{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:AZ7A767KUFBR7AXZM7CQ7NOOBT","short_pith_number":"pith:AZ7A767K","canonical_record":{"source":{"id":"1906.02922","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-07T06:32:25Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d62dc573ad779bb7fa4bc026b6bc523550db88f27217829d8a5225c0a9707e3f","abstract_canon_sha256":"188cac21eb5d104b16cedab8f1950513bd0cb53473ffd0e987f75ab341093e45"},"schema_version":"1.0"},"canonical_sha256":"067e0ffbeaa1431f82f967c50fb5ce0cf3fe08c50613502707cb415db27283f0","source":{"kind":"arxiv","id":"1906.02922","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.02922","created_at":"2026-07-05T01:03:19Z"},{"alias_kind":"arxiv_version","alias_value":"1906.02922v4","created_at":"2026-07-05T01:03:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.02922","created_at":"2026-07-05T01:03:19Z"},{"alias_kind":"pith_short_12","alias_value":"AZ7A767KUFBR","created_at":"2026-07-05T01:03:19Z"},{"alias_kind":"pith_short_16","alias_value":"AZ7A767KUFBR7AXZ","created_at":"2026-07-05T01:03:19Z"},{"alias_kind":"pith_short_8","alias_value":"AZ7A767K","created_at":"2026-07-05T01:03:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:AZ7A767KUFBR7AXZM7CQ7NOOBT","target":"record","payload":{"canonical_record":{"source":{"id":"1906.02922","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-07T06:32:25Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d62dc573ad779bb7fa4bc026b6bc523550db88f27217829d8a5225c0a9707e3f","abstract_canon_sha256":"188cac21eb5d104b16cedab8f1950513bd0cb53473ffd0e987f75ab341093e45"},"schema_version":"1.0"},"canonical_sha256":"067e0ffbeaa1431f82f967c50fb5ce0cf3fe08c50613502707cb415db27283f0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:03:19.352506Z","signature_b64":"WEssMBuR3vEV42Zbs0SiurKkdIblJJisxx4sJ2OJuL/UalaN4kUl1Lz/qBKrzTp5U4ffGGsG3ovwCOVmnKWhCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"067e0ffbeaa1431f82f967c50fb5ce0cf3fe08c50613502707cb415db27283f0","last_reissued_at":"2026-07-05T01:03:19.352017Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:03:19.352017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.02922","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:03:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"346IRsS9bvrjoAUeoEWxF5Oxze0yd/IJky4cPsdsDvl1XW1IMfAsMek66oPWF6BfFLi1jq2LIFWIhiB6tn6FAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:44:23.470364Z"},"content_sha256":"975ccd57df433b622bc233efb3d97a267d0439b83a84dcf1f3f405ae3dbe1896","schema_version":"1.0","event_id":"sha256:975ccd57df433b622bc233efb3d97a267d0439b83a84dcf1f3f405ae3dbe1896"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:AZ7A767KUFBR7AXZM7CQ7NOOBT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Non-Stationary Reinforcement Learning: The Blessing of (More) Optimism","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Simchi-Levi, Ruihao Zhu, Wang Chi Cheung","submitted_at":"2019-06-07T06:32:25Z","abstract_excerpt":"We consider un-discounted reinforcement learning (RL) in Markov decision processes (MDPs) under temporal drifts, ie, both the reward and state transition distributions are allowed to evolve over time, as long as their respective total variations, quantified by suitable metrics, do not exceed certain variation budgets. This setting captures the endogeneity, exogeneity, uncertainty, and partial feedback in sequential decision-making scenarios, and finds applications in vehicle remarketing and real-time bidding. We first develop the Sliding Window Upper-Confidence bound for Reinforcement Learning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.02922","kind":"arxiv","version":4},"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/1906.02922/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:03:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u/qQT2mP1OicL9wOs7cxv4HGPE0+0baQ8juLQH9wF0GD0lRcy2lIukPCFtArqwrB8Z5B4uXZW/8ZwTvTGRolBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:44:23.470770Z"},"content_sha256":"bcf079518c45fd1eee5d2fc086f3dc44c1153e19454c333b296435d9a840e9f9","schema_version":"1.0","event_id":"sha256:bcf079518c45fd1eee5d2fc086f3dc44c1153e19454c333b296435d9a840e9f9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AZ7A767KUFBR7AXZM7CQ7NOOBT/bundle.json","state_url":"https://pith.science/pith/AZ7A767KUFBR7AXZM7CQ7NOOBT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AZ7A767KUFBR7AXZM7CQ7NOOBT/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":"2026-07-07T08:44:23Z","links":{"resolver":"https://pith.science/pith/AZ7A767KUFBR7AXZM7CQ7NOOBT","bundle":"https://pith.science/pith/AZ7A767KUFBR7AXZM7CQ7NOOBT/bundle.json","state":"https://pith.science/pith/AZ7A767KUFBR7AXZM7CQ7NOOBT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AZ7A767KUFBR7AXZM7CQ7NOOBT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:AZ7A767KUFBR7AXZM7CQ7NOOBT","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":"188cac21eb5d104b16cedab8f1950513bd0cb53473ffd0e987f75ab341093e45","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-07T06:32:25Z","title_canon_sha256":"d62dc573ad779bb7fa4bc026b6bc523550db88f27217829d8a5225c0a9707e3f"},"schema_version":"1.0","source":{"id":"1906.02922","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.02922","created_at":"2026-07-05T01:03:19Z"},{"alias_kind":"arxiv_version","alias_value":"1906.02922v4","created_at":"2026-07-05T01:03:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.02922","created_at":"2026-07-05T01:03:19Z"},{"alias_kind":"pith_short_12","alias_value":"AZ7A767KUFBR","created_at":"2026-07-05T01:03:19Z"},{"alias_kind":"pith_short_16","alias_value":"AZ7A767KUFBR7AXZ","created_at":"2026-07-05T01:03:19Z"},{"alias_kind":"pith_short_8","alias_value":"AZ7A767K","created_at":"2026-07-05T01:03:19Z"}],"graph_snapshots":[{"event_id":"sha256:bcf079518c45fd1eee5d2fc086f3dc44c1153e19454c333b296435d9a840e9f9","target":"graph","created_at":"2026-07-05T01:03:19Z","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/1906.02922/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider un-discounted reinforcement learning (RL) in Markov decision processes (MDPs) under temporal drifts, ie, both the reward and state transition distributions are allowed to evolve over time, as long as their respective total variations, quantified by suitable metrics, do not exceed certain variation budgets. This setting captures the endogeneity, exogeneity, uncertainty, and partial feedback in sequential decision-making scenarios, and finds applications in vehicle remarketing and real-time bidding. We first develop the Sliding Window Upper-Confidence bound for Reinforcement Learning","authors_text":"David Simchi-Levi, Ruihao Zhu, Wang Chi Cheung","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-07T06:32:25Z","title":"Non-Stationary Reinforcement Learning: The Blessing of (More) Optimism"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.02922","kind":"arxiv","version":4},"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":"sha256:975ccd57df433b622bc233efb3d97a267d0439b83a84dcf1f3f405ae3dbe1896","target":"record","created_at":"2026-07-05T01:03:19Z","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":"188cac21eb5d104b16cedab8f1950513bd0cb53473ffd0e987f75ab341093e45","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-07T06:32:25Z","title_canon_sha256":"d62dc573ad779bb7fa4bc026b6bc523550db88f27217829d8a5225c0a9707e3f"},"schema_version":"1.0","source":{"id":"1906.02922","kind":"arxiv","version":4}},"canonical_sha256":"067e0ffbeaa1431f82f967c50fb5ce0cf3fe08c50613502707cb415db27283f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"067e0ffbeaa1431f82f967c50fb5ce0cf3fe08c50613502707cb415db27283f0","first_computed_at":"2026-07-05T01:03:19.352017Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:03:19.352017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WEssMBuR3vEV42Zbs0SiurKkdIblJJisxx4sJ2OJuL/UalaN4kUl1Lz/qBKrzTp5U4ffGGsG3ovwCOVmnKWhCg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:03:19.352506Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.02922","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:975ccd57df433b622bc233efb3d97a267d0439b83a84dcf1f3f405ae3dbe1896","sha256:bcf079518c45fd1eee5d2fc086f3dc44c1153e19454c333b296435d9a840e9f9"],"state_sha256":"38ac4264e594a6f8549990dc15a05137195c2c5fd989989c2ff6714b7fec620a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d2NRo3f4FhKJKq1f6FSaQA/XHRMJyN4MoCTBt9bV31UPiM4vVfmYOlcriyRcKB1CiCZH0aLsPGRhEf3yQkq2Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:44:23.472695Z","bundle_sha256":"94a350fdf7eb01501d7a0e5c48232b0550fcd283177123a989100305f6ae0aaa"}}