{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ORZRPBPBHTNO4KVYPTX74LW72P","short_pith_number":"pith:ORZRPBPB","schema_version":"1.0","canonical_sha256":"74731785e13cdaee2ab87ceffe2edfd3e08a7fe072a8e01a29f9b4b3e0ce2665","source":{"kind":"arxiv","id":"2112.01585","version":2},"attestation_state":"computed","paper":{"title":"Differentially Private Exploration in Reinforcement Learning with Linear Representation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alessandro Lazaric, Evrard Garcelon, Matteo Pirotta, Paul Luyo","submitted_at":"2021-12-02T19:59:50Z","abstract_excerpt":"This paper studies privacy-preserving exploration in Markov Decision Processes (MDPs) with linear representation. We first consider the setting of linear-mixture MDPs (Ayoub et al., 2020) (a.k.a.\\ model-based setting) and provide an unified framework for analyzing joint and local differential private (DP) exploration. Through this framework, we prove a $\\widetilde{O}(K^{3/4}/\\sqrt{\\epsilon})$ regret bound for $(\\epsilon,\\delta)$-local DP exploration and a $\\widetilde{O}(\\sqrt{K/\\epsilon})$ regret bound for $(\\epsilon,\\delta)$-joint DP. We further study privacy-preserving exploration in linear "},"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":"2112.01585","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-02T19:59:50Z","cross_cats_sorted":[],"title_canon_sha256":"1e1ad80074b9f7058323e3791e063122983dfc18dfb88add4d5d060fb5b06f6c","abstract_canon_sha256":"06630d39ebb08dbab9bd99171bd82b3b2c8bc9dd16e6849f9b6d5e0d8276c0e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:38:43.321831Z","signature_b64":"vfA00a1k/dX9+MhXrnZyYUMTfueCAU3oKR3eh2runbkFphWQGlFrGAnED3+GnMmYmKprn2ou7vukIs0PGFabAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74731785e13cdaee2ab87ceffe2edfd3e08a7fe072a8e01a29f9b4b3e0ce2665","last_reissued_at":"2026-07-05T03:38:43.321362Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:38:43.321362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentially Private Exploration in Reinforcement Learning with Linear Representation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alessandro Lazaric, Evrard Garcelon, Matteo Pirotta, Paul Luyo","submitted_at":"2021-12-02T19:59:50Z","abstract_excerpt":"This paper studies privacy-preserving exploration in Markov Decision Processes (MDPs) with linear representation. We first consider the setting of linear-mixture MDPs (Ayoub et al., 2020) (a.k.a.\\ model-based setting) and provide an unified framework for analyzing joint and local differential private (DP) exploration. Through this framework, we prove a $\\widetilde{O}(K^{3/4}/\\sqrt{\\epsilon})$ regret bound for $(\\epsilon,\\delta)$-local DP exploration and a $\\widetilde{O}(\\sqrt{K/\\epsilon})$ regret bound for $(\\epsilon,\\delta)$-joint DP. We further study privacy-preserving exploration in linear "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.01585","kind":"arxiv","version":2},"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/2112.01585/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":"2112.01585","created_at":"2026-07-05T03:38:43.321421+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.01585v2","created_at":"2026-07-05T03:38:43.321421+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.01585","created_at":"2026-07-05T03:38:43.321421+00:00"},{"alias_kind":"pith_short_12","alias_value":"ORZRPBPBHTNO","created_at":"2026-07-05T03:38:43.321421+00:00"},{"alias_kind":"pith_short_16","alias_value":"ORZRPBPBHTNO4KVY","created_at":"2026-07-05T03:38:43.321421+00:00"},{"alias_kind":"pith_short_8","alias_value":"ORZRPBPB","created_at":"2026-07-05T03:38:43.321421+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23131","citing_title":"When Determinants Are Not Enough: Private Rare Switching","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2510.21060","citing_title":"On the Sample Complexity of Differentially Private Policy Optimization","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ORZRPBPBHTNO4KVYPTX74LW72P","json":"https://pith.science/pith/ORZRPBPBHTNO4KVYPTX74LW72P.json","graph_json":"https://pith.science/api/pith-number/ORZRPBPBHTNO4KVYPTX74LW72P/graph.json","events_json":"https://pith.science/api/pith-number/ORZRPBPBHTNO4KVYPTX74LW72P/events.json","paper":"https://pith.science/paper/ORZRPBPB"},"agent_actions":{"view_html":"https://pith.science/pith/ORZRPBPBHTNO4KVYPTX74LW72P","download_json":"https://pith.science/pith/ORZRPBPBHTNO4KVYPTX74LW72P.json","view_paper":"https://pith.science/paper/ORZRPBPB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.01585&json=true","fetch_graph":"https://pith.science/api/pith-number/ORZRPBPBHTNO4KVYPTX74LW72P/graph.json","fetch_events":"https://pith.science/api/pith-number/ORZRPBPBHTNO4KVYPTX74LW72P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ORZRPBPBHTNO4KVYPTX74LW72P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ORZRPBPBHTNO4KVYPTX74LW72P/action/storage_attestation","attest_author":"https://pith.science/pith/ORZRPBPBHTNO4KVYPTX74LW72P/action/author_attestation","sign_citation":"https://pith.science/pith/ORZRPBPBHTNO4KVYPTX74LW72P/action/citation_signature","submit_replication":"https://pith.science/pith/ORZRPBPBHTNO4KVYPTX74LW72P/action/replication_record"}},"created_at":"2026-07-05T03:38:43.321421+00:00","updated_at":"2026-07-05T03:38:43.321421+00:00"}