{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:X2DPYUYOCSDHM3YJOXGXBR562T","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":"1018d04055db6c85aabae60d1f54be0be7458a7a9ccf7027d0cf66809dc2e362","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-08T16:17:53Z","title_canon_sha256":"0b985595a49f23c207bd746b2e55776a2e8165967a8d79e168ddce9fab79ff81"},"schema_version":"1.0","source":{"id":"2010.04091","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.04091","created_at":"2026-07-05T01:41:26Z"},{"alias_kind":"arxiv_version","alias_value":"2010.04091v1","created_at":"2026-07-05T01:41:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.04091","created_at":"2026-07-05T01:41:26Z"},{"alias_kind":"pith_short_12","alias_value":"X2DPYUYOCSDH","created_at":"2026-07-05T01:41:26Z"},{"alias_kind":"pith_short_16","alias_value":"X2DPYUYOCSDHM3YJ","created_at":"2026-07-05T01:41:26Z"},{"alias_kind":"pith_short_8","alias_value":"X2DPYUYO","created_at":"2026-07-05T01:41:26Z"}],"graph_snapshots":[{"event_id":"sha256:5ccca7e7639b98310d6b0e6c1f48caa5d4be314b59396a48bbc2cd30261de655","target":"graph","created_at":"2026-07-05T01:41:26Z","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/2010.04091/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modifying the reward-biased maximum likelihood method originally proposed in the adaptive control literature, we propose novel learning algorithms to handle the explore-exploit trade-off in linear bandits problems as well as generalized linear bandits problems. We develop novel index policies that we prove achieve order-optimality, and show that they achieve empirical performance competitive with the state-of-the-art benchmark methods in extensive experiments. The new policies achieve this with low computation time per pull for linear bandits, and thereby resulting in both favorable regret as ","authors_text":"Ping-Chun Hsieh, P. R. Kumar, Xi Liu, Yu-Heng Hung","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-08T16:17:53Z","title":"Reward-Biased Maximum Likelihood Estimation for Linear Stochastic Bandits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.04091","kind":"arxiv","version":1},"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":"sha256:05ba746be08b36bffdf78edae109e8c42f60462e757b2031983f68465aec8aee","target":"record","created_at":"2026-07-05T01:41:26Z","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":"1018d04055db6c85aabae60d1f54be0be7458a7a9ccf7027d0cf66809dc2e362","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-08T16:17:53Z","title_canon_sha256":"0b985595a49f23c207bd746b2e55776a2e8165967a8d79e168ddce9fab79ff81"},"schema_version":"1.0","source":{"id":"2010.04091","kind":"arxiv","version":1}},"canonical_sha256":"be86fc530e1486766f0975cd70c7bed4c0d9fe1d472ee6f85f2e2eb1db259997","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be86fc530e1486766f0975cd70c7bed4c0d9fe1d472ee6f85f2e2eb1db259997","first_computed_at":"2026-07-05T01:41:26.851480Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:41:26.851480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dA8qj/ZscbZ/aorvutsIJQG50AQ/gfgIynfGxn0bI362KFcAk7NO3ipC9qav0Ihp+nOl4V5Vmj4IInypJLd5AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:41:26.851894Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.04091","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05ba746be08b36bffdf78edae109e8c42f60462e757b2031983f68465aec8aee","sha256:5ccca7e7639b98310d6b0e6c1f48caa5d4be314b59396a48bbc2cd30261de655"],"state_sha256":"0a3376ddfd98288082a062898998aafb5fe66980f39920f82705b1251ba36205"}