{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IDFQIQ7YK2TSMHXTJUDCQUODPZ","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":"b79e39ae281e4df3594aecebd62660dbbf70b4ab9fa52104bda07b2469e5d2af","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-12T02:56:09Z","title_canon_sha256":"b357f179cec1287c9ea99c2735119288e35d63707aa8d9184c32dcdf86520e19"},"schema_version":"1.0","source":{"id":"2306.06836","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.06836","created_at":"2026-07-05T07:53:08Z"},{"alias_kind":"arxiv_version","alias_value":"2306.06836v3","created_at":"2026-07-05T07:53:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.06836","created_at":"2026-07-05T07:53:08Z"},{"alias_kind":"pith_short_12","alias_value":"IDFQIQ7YK2TS","created_at":"2026-07-05T07:53:08Z"},{"alias_kind":"pith_short_16","alias_value":"IDFQIQ7YK2TSMHXT","created_at":"2026-07-05T07:53:08Z"},{"alias_kind":"pith_short_8","alias_value":"IDFQIQ7Y","created_at":"2026-07-05T07:53:08Z"}],"graph_snapshots":[{"event_id":"sha256:3959962c2c6bde6a11733e313dbd0e439241adae86a9e4d7bec635a987c1d53b","target":"graph","created_at":"2026-07-05T07:53:08Z","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/2306.06836/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Han Zhong, Jiayi Huang, Lin F. Yang, Liwei Wang","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-12T02:56:09Z","title":"Tackling Heavy-Tailed Rewards in Reinforcement Learning with Function Approximation: Minimax Optimal and Instance-Dependent Regret Bounds"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.06836","kind":"arxiv","version":3},"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":"sha256:084be533098dfdbb9805cfd768824b1532257ea406575f26e6b8e070d403f9b3","target":"record","created_at":"2026-07-05T07:53:08Z","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":"b79e39ae281e4df3594aecebd62660dbbf70b4ab9fa52104bda07b2469e5d2af","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-12T02:56:09Z","title_canon_sha256":"b357f179cec1287c9ea99c2735119288e35d63707aa8d9184c32dcdf86520e19"},"schema_version":"1.0","source":{"id":"2306.06836","kind":"arxiv","version":3}},"canonical_sha256":"40cb0443f856a7261ef34d062851c37e418af6d8be74dee0e45c2f3b65398cb8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"40cb0443f856a7261ef34d062851c37e418af6d8be74dee0e45c2f3b65398cb8","first_computed_at":"2026-07-05T07:53:08.648043Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:53:08.648043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bjvYxT/cZ3ZyNyp3vER7OzCcUsndnrRTV6eLGlMOT8GNETTrqaSKOxodt+ov1EvMIBFTghXv7ua50cFrzR5ZBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:53:08.648534Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.06836","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:084be533098dfdbb9805cfd768824b1532257ea406575f26e6b8e070d403f9b3","sha256:3959962c2c6bde6a11733e313dbd0e439241adae86a9e4d7bec635a987c1d53b"],"state_sha256":"e003325d35f65247cefad81c61eaf4c16bc388332579afc51eb94e3ca5a4be1a"}