{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:P2VR2UKS75ZW2LS3LIPM7XPDMW","short_pith_number":"pith:P2VR2UKS","schema_version":"1.0","canonical_sha256":"7eab1d5152ff736d2e5b5a1ecfdde365838af7c57f2cfe2f3dcac318de8658be","source":{"kind":"arxiv","id":"2102.05406","version":3},"attestation_state":"computed","paper":{"title":"Non-stationary Reinforcement Learning without Prior Knowledge: An Optimal Black-box Approach","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chen-Yu Wei, Haipeng Luo","submitted_at":"2021-02-10T12:43:31Z","abstract_excerpt":"We propose a black-box reduction that turns a certain reinforcement learning algorithm with optimal regret in a (near-)stationary environment into another algorithm with optimal dynamic regret in a non-stationary environment, importantly without any prior knowledge on the degree of non-stationarity. By plugging different algorithms into our black-box, we provide a list of examples showing that our approach not only recovers recent results for (contextual) multi-armed bandits achieved by very specialized algorithms, but also significantly improves the state of the art for (generalized) linear b"},"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":"2102.05406","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-10T12:43:31Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"3d079d5d96b8466d82d9c806dc3a243130aefb31fd6086f25bd4919b20000b36","abstract_canon_sha256":"a879c27db1bf6953b81092bb8863f5ee0c923b425443231814befad76b8e9b01"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:11:27.901645Z","signature_b64":"xv6SOfPKN0QnIGT6ZuUoM1lC4oSgVsJoZfol6UVZz8YpjoFUtNTpFcm1lHuvBfwVWLZKAWCiiFznMsPBidiGAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7eab1d5152ff736d2e5b5a1ecfdde365838af7c57f2cfe2f3dcac318de8658be","last_reissued_at":"2026-07-05T03:11:27.901227Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:11:27.901227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Non-stationary Reinforcement Learning without Prior Knowledge: An Optimal Black-box Approach","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chen-Yu Wei, Haipeng Luo","submitted_at":"2021-02-10T12:43:31Z","abstract_excerpt":"We propose a black-box reduction that turns a certain reinforcement learning algorithm with optimal regret in a (near-)stationary environment into another algorithm with optimal dynamic regret in a non-stationary environment, importantly without any prior knowledge on the degree of non-stationarity. By plugging different algorithms into our black-box, we provide a list of examples showing that our approach not only recovers recent results for (contextual) multi-armed bandits achieved by very specialized algorithms, but also significantly improves the state of the art for (generalized) linear b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.05406","kind":"arxiv","version":3},"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/2102.05406/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":"2102.05406","created_at":"2026-07-05T03:11:27.901292+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.05406v3","created_at":"2026-07-05T03:11:27.901292+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.05406","created_at":"2026-07-05T03:11:27.901292+00:00"},{"alias_kind":"pith_short_12","alias_value":"P2VR2UKS75ZW","created_at":"2026-07-05T03:11:27.901292+00:00"},{"alias_kind":"pith_short_16","alias_value":"P2VR2UKS75ZW2LS3","created_at":"2026-07-05T03:11:27.901292+00:00"},{"alias_kind":"pith_short_8","alias_value":"P2VR2UKS","created_at":"2026-07-05T03:11:27.901292+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29092","citing_title":"Priced Motion Through Optimal Faces: A Normal-Fan Geometry for Non-Stationary Adversarial MDPs","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P2VR2UKS75ZW2LS3LIPM7XPDMW","json":"https://pith.science/pith/P2VR2UKS75ZW2LS3LIPM7XPDMW.json","graph_json":"https://pith.science/api/pith-number/P2VR2UKS75ZW2LS3LIPM7XPDMW/graph.json","events_json":"https://pith.science/api/pith-number/P2VR2UKS75ZW2LS3LIPM7XPDMW/events.json","paper":"https://pith.science/paper/P2VR2UKS"},"agent_actions":{"view_html":"https://pith.science/pith/P2VR2UKS75ZW2LS3LIPM7XPDMW","download_json":"https://pith.science/pith/P2VR2UKS75ZW2LS3LIPM7XPDMW.json","view_paper":"https://pith.science/paper/P2VR2UKS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.05406&json=true","fetch_graph":"https://pith.science/api/pith-number/P2VR2UKS75ZW2LS3LIPM7XPDMW/graph.json","fetch_events":"https://pith.science/api/pith-number/P2VR2UKS75ZW2LS3LIPM7XPDMW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P2VR2UKS75ZW2LS3LIPM7XPDMW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P2VR2UKS75ZW2LS3LIPM7XPDMW/action/storage_attestation","attest_author":"https://pith.science/pith/P2VR2UKS75ZW2LS3LIPM7XPDMW/action/author_attestation","sign_citation":"https://pith.science/pith/P2VR2UKS75ZW2LS3LIPM7XPDMW/action/citation_signature","submit_replication":"https://pith.science/pith/P2VR2UKS75ZW2LS3LIPM7XPDMW/action/replication_record"}},"created_at":"2026-07-05T03:11:27.901292+00:00","updated_at":"2026-07-05T03:11:27.901292+00:00"}