{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IDFQIQ7YK2TSMHXTJUDCQUODPZ","short_pith_number":"pith:IDFQIQ7Y","schema_version":"1.0","canonical_sha256":"40cb0443f856a7261ef34d062851c37e418af6d8be74dee0e45c2f3b65398cb8","source":{"kind":"arxiv","id":"2306.06836","version":3},"attestation_state":"computed","paper":{"title":"Tackling Heavy-Tailed Rewards in Reinforcement Learning with Function Approximation: Minimax Optimal and Instance-Dependent Regret Bounds","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Han Zhong, Jiayi Huang, Lin F. Yang, Liwei Wang","submitted_at":"2023-06-12T02:56:09Z","abstract_excerpt":"While numerous works have focused on devising efficient algorithms for reinforcement learning (RL) with uniformly bounded rewards, it remains an open question whether sample or time-efficient algorithms for RL with large state-action space exist when the rewards are \\emph{heavy-tailed}, i.e., with only finite $(1+\\epsilon)$-th moments for some $\\epsilon\\in(0,1]$. In this work, we address the challenge of such rewards in RL with linear function approximation. We first design an algorithm, \\textsc{Heavy-OFUL}, for heavy-tailed linear bandits, achieving an \\emph{instance-dependent} $T$-round regr"},"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":"2306.06836","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-12T02:56:09Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"b357f179cec1287c9ea99c2735119288e35d63707aa8d9184c32dcdf86520e19","abstract_canon_sha256":"b79e39ae281e4df3594aecebd62660dbbf70b4ab9fa52104bda07b2469e5d2af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:53:08.648534Z","signature_b64":"bjvYxT/cZ3ZyNyp3vER7OzCcUsndnrRTV6eLGlMOT8GNETTrqaSKOxodt+ov1EvMIBFTghXv7ua50cFrzR5ZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40cb0443f856a7261ef34d062851c37e418af6d8be74dee0e45c2f3b65398cb8","last_reissued_at":"2026-07-05T07:53:08.648043Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:53:08.648043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tackling Heavy-Tailed Rewards in Reinforcement Learning with Function Approximation: Minimax Optimal and Instance-Dependent Regret Bounds","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Han Zhong, Jiayi Huang, Lin F. Yang, Liwei Wang","submitted_at":"2023-06-12T02:56:09Z","abstract_excerpt":"While numerous works have focused on devising efficient algorithms for reinforcement learning (RL) with uniformly bounded rewards, it remains an open question whether sample or time-efficient algorithms for RL with large state-action space exist when the rewards are \\emph{heavy-tailed}, i.e., with only finite $(1+\\epsilon)$-th moments for some $\\epsilon\\in(0,1]$. In this work, we address the challenge of such rewards in RL with linear function approximation. We first design an algorithm, \\textsc{Heavy-OFUL}, for heavy-tailed linear bandits, achieving an \\emph{instance-dependent} $T$-round regr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.06836","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/2306.06836/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":"2306.06836","created_at":"2026-07-05T07:53:08.648103+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.06836v3","created_at":"2026-07-05T07:53:08.648103+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.06836","created_at":"2026-07-05T07:53:08.648103+00:00"},{"alias_kind":"pith_short_12","alias_value":"IDFQIQ7YK2TS","created_at":"2026-07-05T07:53:08.648103+00:00"},{"alias_kind":"pith_short_16","alias_value":"IDFQIQ7YK2TSMHXT","created_at":"2026-07-05T07:53:08.648103+00:00"},{"alias_kind":"pith_short_8","alias_value":"IDFQIQ7Y","created_at":"2026-07-05T07:53:08.648103+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IDFQIQ7YK2TSMHXTJUDCQUODPZ","json":"https://pith.science/pith/IDFQIQ7YK2TSMHXTJUDCQUODPZ.json","graph_json":"https://pith.science/api/pith-number/IDFQIQ7YK2TSMHXTJUDCQUODPZ/graph.json","events_json":"https://pith.science/api/pith-number/IDFQIQ7YK2TSMHXTJUDCQUODPZ/events.json","paper":"https://pith.science/paper/IDFQIQ7Y"},"agent_actions":{"view_html":"https://pith.science/pith/IDFQIQ7YK2TSMHXTJUDCQUODPZ","download_json":"https://pith.science/pith/IDFQIQ7YK2TSMHXTJUDCQUODPZ.json","view_paper":"https://pith.science/paper/IDFQIQ7Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.06836&json=true","fetch_graph":"https://pith.science/api/pith-number/IDFQIQ7YK2TSMHXTJUDCQUODPZ/graph.json","fetch_events":"https://pith.science/api/pith-number/IDFQIQ7YK2TSMHXTJUDCQUODPZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IDFQIQ7YK2TSMHXTJUDCQUODPZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IDFQIQ7YK2TSMHXTJUDCQUODPZ/action/storage_attestation","attest_author":"https://pith.science/pith/IDFQIQ7YK2TSMHXTJUDCQUODPZ/action/author_attestation","sign_citation":"https://pith.science/pith/IDFQIQ7YK2TSMHXTJUDCQUODPZ/action/citation_signature","submit_replication":"https://pith.science/pith/IDFQIQ7YK2TSMHXTJUDCQUODPZ/action/replication_record"}},"created_at":"2026-07-05T07:53:08.648103+00:00","updated_at":"2026-07-05T07:53:08.648103+00:00"}