{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:3FS5KGFDLWMT4ZNZRLFM3CCO4I","short_pith_number":"pith:3FS5KGFD","canonical_record":{"source":{"id":"2102.12769","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-25T10:25:57Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d584e0a4a2831408d614bcfa6d85c9eabd9833020e9398dc75b4d64a282e4e5c","abstract_canon_sha256":"99eb1f0090ef804fef53dacaf17251258fe0d91f5aaaa46e47784e331e168b19"},"schema_version":"1.0"},"canonical_sha256":"d965d518a35d993e65b98acacd884ee22410b66cc2a9b0dbe82844fefd9c8cc9","source":{"kind":"arxiv","id":"2102.12769","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.12769","created_at":"2026-07-05T02:18:23Z"},{"alias_kind":"arxiv_version","alias_value":"2102.12769v1","created_at":"2026-07-05T02:18:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.12769","created_at":"2026-07-05T02:18:23Z"},{"alias_kind":"pith_short_12","alias_value":"3FS5KGFDLWMT","created_at":"2026-07-05T02:18:23Z"},{"alias_kind":"pith_short_16","alias_value":"3FS5KGFDLWMT4ZNZ","created_at":"2026-07-05T02:18:23Z"},{"alias_kind":"pith_short_8","alias_value":"3FS5KGFD","created_at":"2026-07-05T02:18:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:3FS5KGFDLWMT4ZNZRLFM3CCO4I","target":"record","payload":{"canonical_record":{"source":{"id":"2102.12769","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-25T10:25:57Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d584e0a4a2831408d614bcfa6d85c9eabd9833020e9398dc75b4d64a282e4e5c","abstract_canon_sha256":"99eb1f0090ef804fef53dacaf17251258fe0d91f5aaaa46e47784e331e168b19"},"schema_version":"1.0"},"canonical_sha256":"d965d518a35d993e65b98acacd884ee22410b66cc2a9b0dbe82844fefd9c8cc9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:18:23.634769Z","signature_b64":"dkj//KQgvZK7oA1yhHs9QM5CdH0Mu1CnRAaezd+y+7eziV0UqE91fCwDOoDF9uk0P8ZCF7VbFf5bgKl7IXMeAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d965d518a35d993e65b98acacd884ee22410b66cc2a9b0dbe82844fefd9c8cc9","last_reissued_at":"2026-07-05T02:18:23.634312Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:18:23.634312Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.12769","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:18:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jKSvlZdq+74aSPHkG3+83OsjzutNf6GyPgmnhT/Ef9vaJzCA2mjyQbTDK4ZMg0zTCsW+NIpPXuB9NqTKlmUeCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:10:35.228209Z"},"content_sha256":"068f6b2684b54caef4b683a75e50e89c8a9ff93d306b4016e2967d4b1c774fd1","schema_version":"1.0","event_id":"sha256:068f6b2684b54caef4b683a75e50e89c8a9ff93d306b4016e2967d4b1c774fd1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:3FS5KGFDLWMT4ZNZRLFM3CCO4I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"No-Regret Reinforcement Learning with Heavy-Tailed Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Vincent Zhuang, Yanan Sui","submitted_at":"2021-02-25T10:25:57Z","abstract_excerpt":"Reinforcement learning algorithms typically assume rewards to be sampled from light-tailed distributions, such as Gaussian or bounded. However, a wide variety of real-world systems generate rewards that follow heavy-tailed distributions. We consider such scenarios in the setting of undiscounted reinforcement learning. By constructing a lower bound, we show that the difficulty of learning heavy-tailed rewards asymptotically dominates the difficulty of learning transition probabilities. Leveraging techniques from robust mean estimation, we propose Heavy-UCRL2 and Heavy-Q-Learning, and show that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.12769","kind":"arxiv","version":1},"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/2102.12769/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":"2026-07-05T02:18:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rYlN2esCWLob7Z6A1/6GRMKfgP+vsl8nHjSB+7Moc1XwntSKQ4jbY2wKdNZ962ebX4uPkIJktPXp2UwXlxWhCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:10:35.228699Z"},"content_sha256":"a381e4c7bf169795448b90a49fa7a6917fcf79c467884bacaedd1ae28c93de2f","schema_version":"1.0","event_id":"sha256:a381e4c7bf169795448b90a49fa7a6917fcf79c467884bacaedd1ae28c93de2f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3FS5KGFDLWMT4ZNZRLFM3CCO4I/bundle.json","state_url":"https://pith.science/pith/3FS5KGFDLWMT4ZNZRLFM3CCO4I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3FS5KGFDLWMT4ZNZRLFM3CCO4I/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":"2026-08-04T09:10:35Z","links":{"resolver":"https://pith.science/pith/3FS5KGFDLWMT4ZNZRLFM3CCO4I","bundle":"https://pith.science/pith/3FS5KGFDLWMT4ZNZRLFM3CCO4I/bundle.json","state":"https://pith.science/pith/3FS5KGFDLWMT4ZNZRLFM3CCO4I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3FS5KGFDLWMT4ZNZRLFM3CCO4I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3FS5KGFDLWMT4ZNZRLFM3CCO4I","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":"99eb1f0090ef804fef53dacaf17251258fe0d91f5aaaa46e47784e331e168b19","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-25T10:25:57Z","title_canon_sha256":"d584e0a4a2831408d614bcfa6d85c9eabd9833020e9398dc75b4d64a282e4e5c"},"schema_version":"1.0","source":{"id":"2102.12769","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.12769","created_at":"2026-07-05T02:18:23Z"},{"alias_kind":"arxiv_version","alias_value":"2102.12769v1","created_at":"2026-07-05T02:18:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.12769","created_at":"2026-07-05T02:18:23Z"},{"alias_kind":"pith_short_12","alias_value":"3FS5KGFDLWMT","created_at":"2026-07-05T02:18:23Z"},{"alias_kind":"pith_short_16","alias_value":"3FS5KGFDLWMT4ZNZ","created_at":"2026-07-05T02:18:23Z"},{"alias_kind":"pith_short_8","alias_value":"3FS5KGFD","created_at":"2026-07-05T02:18:23Z"}],"graph_snapshots":[{"event_id":"sha256:a381e4c7bf169795448b90a49fa7a6917fcf79c467884bacaedd1ae28c93de2f","target":"graph","created_at":"2026-07-05T02:18:23Z","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/2102.12769/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning algorithms typically assume rewards to be sampled from light-tailed distributions, such as Gaussian or bounded. However, a wide variety of real-world systems generate rewards that follow heavy-tailed distributions. We consider such scenarios in the setting of undiscounted reinforcement learning. By constructing a lower bound, we show that the difficulty of learning heavy-tailed rewards asymptotically dominates the difficulty of learning transition probabilities. Leveraging techniques from robust mean estimation, we propose Heavy-UCRL2 and Heavy-Q-Learning, and show that ","authors_text":"Vincent Zhuang, Yanan Sui","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-25T10:25:57Z","title":"No-Regret Reinforcement Learning with Heavy-Tailed Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.12769","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":"sha256:068f6b2684b54caef4b683a75e50e89c8a9ff93d306b4016e2967d4b1c774fd1","target":"record","created_at":"2026-07-05T02:18:23Z","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":"99eb1f0090ef804fef53dacaf17251258fe0d91f5aaaa46e47784e331e168b19","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-25T10:25:57Z","title_canon_sha256":"d584e0a4a2831408d614bcfa6d85c9eabd9833020e9398dc75b4d64a282e4e5c"},"schema_version":"1.0","source":{"id":"2102.12769","kind":"arxiv","version":1}},"canonical_sha256":"d965d518a35d993e65b98acacd884ee22410b66cc2a9b0dbe82844fefd9c8cc9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d965d518a35d993e65b98acacd884ee22410b66cc2a9b0dbe82844fefd9c8cc9","first_computed_at":"2026-07-05T02:18:23.634312Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:18:23.634312Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dkj//KQgvZK7oA1yhHs9QM5CdH0Mu1CnRAaezd+y+7eziV0UqE91fCwDOoDF9uk0P8ZCF7VbFf5bgKl7IXMeAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:18:23.634769Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.12769","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:068f6b2684b54caef4b683a75e50e89c8a9ff93d306b4016e2967d4b1c774fd1","sha256:a381e4c7bf169795448b90a49fa7a6917fcf79c467884bacaedd1ae28c93de2f"],"state_sha256":"86253be28795a23320abb4ae5cc8931baa9dbce22e19badb9274bb617119d290"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ewkT8s9tb96MGnxuQXfqUm8ka4KfXBAGxjuKC4rrBkM1VWqTlucqGl/d6yMDd0rIpvRNtUACPqU7Qzq7oChsAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T09:10:35.233039Z","bundle_sha256":"4bc8c9bf2e72a8c671592ad334c13e6447706d09aba4a10794430e9bc2903a3f"}}