{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PLTL7NHWDWCMDMONH2JSBODZFM","short_pith_number":"pith:PLTL7NHW","schema_version":"1.0","canonical_sha256":"7ae6bfb4f61d84c1b1cd3e9320b8792b0d4ecb56ed857665826ee3a207b15a50","source":{"kind":"arxiv","id":"2203.01707","version":4},"attestation_state":"computed","paper":{"title":"Testing Stationarity and Change Point Detection in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chengchun Shi, Mengbing Li, Piotr Fryzlewicz, Zhenke Wu","submitted_at":"2022-03-03T13:30:28Z","abstract_excerpt":"We consider offline reinforcement learning (RL) methods in possibly nonstationary environments. Many existing RL algorithms in the literature rely on the stationarity assumption that requires the system transition and the reward function to be constant over time. However, the stationarity assumption is restrictive in practice and is likely to be violated in a number of applications, including traffic signal control, robotics and mobile health. In this paper, we develop a consistent procedure to test the nonstationarity of the optimal Q-function based on pre-collected historical data, without a"},"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":"2203.01707","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-03-03T13:30:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e1aebced5003683b6e39d35b96f89c64f443a86ead5053454127aa9cf4a3f38a","abstract_canon_sha256":"f001c1602a72a922bc6c96a64550889880098f02fd6937ba8d44ee1c3a9ac51c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:45.534871Z","signature_b64":"Qtv7fkzC4WOO7gLm9zooeLtdsy/TLmXLO947+lBITM/aMkByVrPFqDqNKyH5U3zarRWBiGdT/zDIV5DNmzOuCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ae6bfb4f61d84c1b1cd3e9320b8792b0d4ecb56ed857665826ee3a207b15a50","last_reissued_at":"2026-07-05T09:56:45.534455Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:45.534455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Testing Stationarity and Change Point Detection in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chengchun Shi, Mengbing Li, Piotr Fryzlewicz, Zhenke Wu","submitted_at":"2022-03-03T13:30:28Z","abstract_excerpt":"We consider offline reinforcement learning (RL) methods in possibly nonstationary environments. Many existing RL algorithms in the literature rely on the stationarity assumption that requires the system transition and the reward function to be constant over time. However, the stationarity assumption is restrictive in practice and is likely to be violated in a number of applications, including traffic signal control, robotics and mobile health. In this paper, we develop a consistent procedure to test the nonstationarity of the optimal Q-function based on pre-collected historical data, without a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.01707","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/2203.01707/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":"2203.01707","created_at":"2026-07-05T09:56:45.534516+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.01707v4","created_at":"2026-07-05T09:56:45.534516+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.01707","created_at":"2026-07-05T09:56:45.534516+00:00"},{"alias_kind":"pith_short_12","alias_value":"PLTL7NHWDWCM","created_at":"2026-07-05T09:56:45.534516+00:00"},{"alias_kind":"pith_short_16","alias_value":"PLTL7NHWDWCMDMON","created_at":"2026-07-05T09:56:45.534516+00:00"},{"alias_kind":"pith_short_8","alias_value":"PLTL7NHW","created_at":"2026-07-05T09:56:45.534516+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.20417","citing_title":"Off-Policy Evaluation and Learning for the Future under Non-Stationarity","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PLTL7NHWDWCMDMONH2JSBODZFM","json":"https://pith.science/pith/PLTL7NHWDWCMDMONH2JSBODZFM.json","graph_json":"https://pith.science/api/pith-number/PLTL7NHWDWCMDMONH2JSBODZFM/graph.json","events_json":"https://pith.science/api/pith-number/PLTL7NHWDWCMDMONH2JSBODZFM/events.json","paper":"https://pith.science/paper/PLTL7NHW"},"agent_actions":{"view_html":"https://pith.science/pith/PLTL7NHWDWCMDMONH2JSBODZFM","download_json":"https://pith.science/pith/PLTL7NHWDWCMDMONH2JSBODZFM.json","view_paper":"https://pith.science/paper/PLTL7NHW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.01707&json=true","fetch_graph":"https://pith.science/api/pith-number/PLTL7NHWDWCMDMONH2JSBODZFM/graph.json","fetch_events":"https://pith.science/api/pith-number/PLTL7NHWDWCMDMONH2JSBODZFM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PLTL7NHWDWCMDMONH2JSBODZFM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PLTL7NHWDWCMDMONH2JSBODZFM/action/storage_attestation","attest_author":"https://pith.science/pith/PLTL7NHWDWCMDMONH2JSBODZFM/action/author_attestation","sign_citation":"https://pith.science/pith/PLTL7NHWDWCMDMONH2JSBODZFM/action/citation_signature","submit_replication":"https://pith.science/pith/PLTL7NHWDWCMDMONH2JSBODZFM/action/replication_record"}},"created_at":"2026-07-05T09:56:45.534516+00:00","updated_at":"2026-07-05T09:56:45.534516+00:00"}