{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GVYEH25PCTKU2TWOME6Y5COQ5U","short_pith_number":"pith:GVYEH25P","schema_version":"1.0","canonical_sha256":"357043ebaf14d54d4ece613d8e89d0ed160d26ce276fbc87d4ff138a35b2abd9","source":{"kind":"arxiv","id":"2110.10133","version":1},"attestation_state":"computed","paper":{"title":"Locally Differentially Private Reinforcement Learning for Linear Mixture Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chonghua Liao, Jiafan He, Quanquan Gu","submitted_at":"2021-10-19T17:44:09Z","abstract_excerpt":"Reinforcement learning (RL) algorithms can be used to provide personalized services, which rely on users' private and sensitive data. To protect the users' privacy, privacy-preserving RL algorithms are in demand. In this paper, we study RL with linear function approximation and local differential privacy (LDP) guarantees. We propose a novel $(\\varepsilon, \\delta)$-LDP algorithm for learning a class of Markov decision processes (MDPs) dubbed linear mixture MDPs, and obtains an $\\tilde{\\mathcal{O}}( d^{5/4}H^{7/4}T^{3/4}\\left(\\log(1/\\delta)\\right)^{1/4}\\sqrt{1/\\varepsilon})$ regret, where $d$ is"},"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":"2110.10133","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-19T17:44:09Z","cross_cats_sorted":["cs.CR","math.OC","stat.ML"],"title_canon_sha256":"22e2e178f0a46a7fe1ad7ef793948d9c816c9d9978f38ff9195d69cdef5b0295","abstract_canon_sha256":"ea5f66241d274e00cc9564789ad419b10720c5c87067897b6a13fbe9ffc6c94e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:24:04.291324Z","signature_b64":"xRkVTb404warRgWSTDa+EYXJEz+wY/WdEDsBb9Mx8bJ360rNi/Kaqe/M4ucnrgWdDANfL6sd5/G4zklaw6emBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"357043ebaf14d54d4ece613d8e89d0ed160d26ce276fbc87d4ff138a35b2abd9","last_reissued_at":"2026-07-05T03:24:04.290880Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:24:04.290880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Locally Differentially Private Reinforcement Learning for Linear Mixture Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chonghua Liao, Jiafan He, Quanquan Gu","submitted_at":"2021-10-19T17:44:09Z","abstract_excerpt":"Reinforcement learning (RL) algorithms can be used to provide personalized services, which rely on users' private and sensitive data. To protect the users' privacy, privacy-preserving RL algorithms are in demand. In this paper, we study RL with linear function approximation and local differential privacy (LDP) guarantees. We propose a novel $(\\varepsilon, \\delta)$-LDP algorithm for learning a class of Markov decision processes (MDPs) dubbed linear mixture MDPs, and obtains an $\\tilde{\\mathcal{O}}( d^{5/4}H^{7/4}T^{3/4}\\left(\\log(1/\\delta)\\right)^{1/4}\\sqrt{1/\\varepsilon})$ regret, where $d$ is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.10133","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2110.10133/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":"2110.10133","created_at":"2026-07-05T03:24:04.290940+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.10133v1","created_at":"2026-07-05T03:24:04.290940+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.10133","created_at":"2026-07-05T03:24:04.290940+00:00"},{"alias_kind":"pith_short_12","alias_value":"GVYEH25PCTKU","created_at":"2026-07-05T03:24:04.290940+00:00"},{"alias_kind":"pith_short_16","alias_value":"GVYEH25PCTKU2TWO","created_at":"2026-07-05T03:24:04.290940+00:00"},{"alias_kind":"pith_short_8","alias_value":"GVYEH25P","created_at":"2026-07-05T03:24:04.290940+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23131","citing_title":"When Determinants Are Not Enough: Private Rare Switching","ref_index":70,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GVYEH25PCTKU2TWOME6Y5COQ5U","json":"https://pith.science/pith/GVYEH25PCTKU2TWOME6Y5COQ5U.json","graph_json":"https://pith.science/api/pith-number/GVYEH25PCTKU2TWOME6Y5COQ5U/graph.json","events_json":"https://pith.science/api/pith-number/GVYEH25PCTKU2TWOME6Y5COQ5U/events.json","paper":"https://pith.science/paper/GVYEH25P"},"agent_actions":{"view_html":"https://pith.science/pith/GVYEH25PCTKU2TWOME6Y5COQ5U","download_json":"https://pith.science/pith/GVYEH25PCTKU2TWOME6Y5COQ5U.json","view_paper":"https://pith.science/paper/GVYEH25P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.10133&json=true","fetch_graph":"https://pith.science/api/pith-number/GVYEH25PCTKU2TWOME6Y5COQ5U/graph.json","fetch_events":"https://pith.science/api/pith-number/GVYEH25PCTKU2TWOME6Y5COQ5U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GVYEH25PCTKU2TWOME6Y5COQ5U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GVYEH25PCTKU2TWOME6Y5COQ5U/action/storage_attestation","attest_author":"https://pith.science/pith/GVYEH25PCTKU2TWOME6Y5COQ5U/action/author_attestation","sign_citation":"https://pith.science/pith/GVYEH25PCTKU2TWOME6Y5COQ5U/action/citation_signature","submit_replication":"https://pith.science/pith/GVYEH25PCTKU2TWOME6Y5COQ5U/action/replication_record"}},"created_at":"2026-07-05T03:24:04.290940+00:00","updated_at":"2026-07-05T03:24:04.290940+00:00"}