{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:HDPFMICCLBOC7FK5C2NGG4DXBE","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":"1ff61cc7d4721f646bffdddc375642abac204a072c929c74425009be66c4eec4","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-22T11:52:04Z","title_canon_sha256":"8314c119c9ca1984dd831a9a72e99cf059c03a81a74a9ade82352ccfddac034b"},"schema_version":"1.0","source":{"id":"2106.11692","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.11692","created_at":"2026-07-05T04:05:32Z"},{"alias_kind":"arxiv_version","alias_value":"2106.11692v2","created_at":"2026-07-05T04:05:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.11692","created_at":"2026-07-05T04:05:32Z"},{"alias_kind":"pith_short_12","alias_value":"HDPFMICCLBOC","created_at":"2026-07-05T04:05:32Z"},{"alias_kind":"pith_short_16","alias_value":"HDPFMICCLBOC7FK5","created_at":"2026-07-05T04:05:32Z"},{"alias_kind":"pith_short_8","alias_value":"HDPFMICC","created_at":"2026-07-05T04:05:32Z"}],"graph_snapshots":[{"event_id":"sha256:b2905afb82b4a0b8409a7574a71b6d81b26117c1b344d21a744d59d2f605bd9f","target":"graph","created_at":"2026-07-05T04:05:32Z","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/2106.11692/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present a reduction-based framework for conservative bandits and RL, in which our core technique is to calculate the necessary and sufficient budget obtained from running the baseline policy. For lower bounds, we improve the existing lower bound for conservative multi-armed bandits and obtain new lower bounds for conservative linear bandits, tabular RL and low-rank MDP, through a black-box reduction that turns a certain lower bound in the nonconservative setting into a new lower bound in the conservative setting. For upper bounds, in multi-armed bandits, linear bandits and ta","authors_text":"Alessandro Lazaric, Evrard Garcelon, Han Zhong, Liwei Wang, Matteo Pirotta, Simon S. Du, Tianhao Wu, Yunchang Yang","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-22T11:52:04Z","title":"A Reduction-Based Framework for Conservative Bandits and Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.11692","kind":"arxiv","version":2},"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":"sha256:72f409f6412396697a76d56a1910c6aa6726d91e7c105dc23daee3649de932b6","target":"record","created_at":"2026-07-05T04:05:32Z","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":"1ff61cc7d4721f646bffdddc375642abac204a072c929c74425009be66c4eec4","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-22T11:52:04Z","title_canon_sha256":"8314c119c9ca1984dd831a9a72e99cf059c03a81a74a9ade82352ccfddac034b"},"schema_version":"1.0","source":{"id":"2106.11692","kind":"arxiv","version":2}},"canonical_sha256":"38de562042585c2f955d169a6370770910c157ab27a943dd9310cb2e84c0437f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"38de562042585c2f955d169a6370770910c157ab27a943dd9310cb2e84c0437f","first_computed_at":"2026-07-05T04:05:32.035299Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:05:32.035299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i/X+wyH6A2pVSPQpd/M4Et/BCa8wBHNnGfpsu2s9MG9UeKbVHrym30DN9GkGav4nNH1/xWx2nmHaXtJEkg1nAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:05:32.035793Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.11692","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72f409f6412396697a76d56a1910c6aa6726d91e7c105dc23daee3649de932b6","sha256:b2905afb82b4a0b8409a7574a71b6d81b26117c1b344d21a744d59d2f605bd9f"],"state_sha256":"6735791915836b4726087392e468e1f9f825fa1280185f09fa22771e1aae52c8"}