{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:IDFQIQ7YK2TSMHXTJUDCQUODPZ","short_pith_number":"pith:IDFQIQ7Y","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"},"canonical_sha256":"40cb0443f856a7261ef34d062851c37e418af6d8be74dee0e45c2f3b65398cb8","source":{"kind":"arxiv","id":"2306.06836","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:IDFQIQ7YK2TSMHXTJUDCQUODPZ","target":"record","payload":{"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"},"canonical_sha256":"40cb0443f856a7261ef34d062851c37e418af6d8be74dee0e45c2f3b65398cb8","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"},"source_kind":"arxiv","source_id":"2306.06836","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:53:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hl7bMBLPPg7UY80EOujZ8pO0KZr9OhSLkxE5birTTK48DjDuqaApn0KYm3bSovlvYzYQykZSI+UQdmNdB0DGBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:06:37.966952Z"},"content_sha256":"084be533098dfdbb9805cfd768824b1532257ea406575f26e6b8e070d403f9b3","schema_version":"1.0","event_id":"sha256:084be533098dfdbb9805cfd768824b1532257ea406575f26e6b8e070d403f9b3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:IDFQIQ7YK2TSMHXTJUDCQUODPZ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:53:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cSbxL+hwSawJgcAzuZkbqliqjmDoo874lbnkS1vk2YWpgBFRT44woX3i5GmqUJ8ntEYvkcNMzIsJsS4d0UuADQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:06:37.967679Z"},"content_sha256":"3959962c2c6bde6a11733e313dbd0e439241adae86a9e4d7bec635a987c1d53b","schema_version":"1.0","event_id":"sha256:3959962c2c6bde6a11733e313dbd0e439241adae86a9e4d7bec635a987c1d53b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IDFQIQ7YK2TSMHXTJUDCQUODPZ/bundle.json","state_url":"https://pith.science/pith/IDFQIQ7YK2TSMHXTJUDCQUODPZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IDFQIQ7YK2TSMHXTJUDCQUODPZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T09:06:37Z","links":{"resolver":"https://pith.science/pith/IDFQIQ7YK2TSMHXTJUDCQUODPZ","bundle":"https://pith.science/pith/IDFQIQ7YK2TSMHXTJUDCQUODPZ/bundle.json","state":"https://pith.science/pith/IDFQIQ7YK2TSMHXTJUDCQUODPZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IDFQIQ7YK2TSMHXTJUDCQUODPZ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"902Ccse5p8PW+FNsEGks7FWElDxTjcL/nK75AP+Z6negTN66SyLwnjiQB4Cb+MxKXIDSKhUVkmur2LPGbWkmBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T09:06:37.978624Z","bundle_sha256":"3b075bce9022319ef847769c685f4dc7b6458d05c74badfbfd7abb74a4f401e7"}}