{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FSX7VBC5YMUFBPBJ2JPPE23HYB","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":"40aacd7c94a463b7ef16b8d5a28c7000f431405adf8c3433f106d97f2b9ba9a2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-11T13:25:53Z","title_canon_sha256":"6a4980a2d70f61bb633bb22f25c3c0d2fb72b53a19cce522e26f9171d10afb66"},"schema_version":"1.0","source":{"id":"2402.07198","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.07198","created_at":"2026-07-05T07:44:02Z"},{"alias_kind":"arxiv_version","alias_value":"2402.07198v1","created_at":"2026-07-05T07:44:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07198","created_at":"2026-07-05T07:44:02Z"},{"alias_kind":"pith_short_12","alias_value":"FSX7VBC5YMUF","created_at":"2026-07-05T07:44:02Z"},{"alias_kind":"pith_short_16","alias_value":"FSX7VBC5YMUFBPBJ","created_at":"2026-07-05T07:44:02Z"},{"alias_kind":"pith_short_8","alias_value":"FSX7VBC5","created_at":"2026-07-05T07:44:02Z"}],"graph_snapshots":[{"event_id":"sha256:1e923cd1836063e4822d4854a373db4a8b0d8725e4eb798d3871362d74fe3d56","target":"graph","created_at":"2026-07-05T07:44:02Z","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/2402.07198/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we prove that Distributional Reinforcement Learning (DistRL), which learns the return distribution, can obtain second-order bounds in both online and offline RL in general settings with function approximation. Second-order bounds are instance-dependent bounds that scale with the variance of return, which we prove are tighter than the previously known small-loss bounds of distributional RL. To the best of our knowledge, our results are the first second-order bounds for low-rank MDPs and for offline RL. When specializing to contextual bandits (one-step RL problem), we show that a ","authors_text":"Alekh Agarwal, Kaiwen Wang, Nathan Kallus, Owen Oertell, Wen Sun","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-11T13:25:53Z","title":"More Benefits of Being Distributional: Second-Order Bounds for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07198","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":"sha256:6d4092b1ab69eccb56761b71201637b351d1b59aaecfe5c79598d20f50ab2f9a","target":"record","created_at":"2026-07-05T07:44:02Z","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":"40aacd7c94a463b7ef16b8d5a28c7000f431405adf8c3433f106d97f2b9ba9a2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-11T13:25:53Z","title_canon_sha256":"6a4980a2d70f61bb633bb22f25c3c0d2fb72b53a19cce522e26f9171d10afb66"},"schema_version":"1.0","source":{"id":"2402.07198","kind":"arxiv","version":1}},"canonical_sha256":"2caffa845dc32850bc29d25ef26b67c059cd2489f107ed815b432f5a6d549432","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2caffa845dc32850bc29d25ef26b67c059cd2489f107ed815b432f5a6d549432","first_computed_at":"2026-07-05T07:44:02.452600Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:44:02.452600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"++1C4ww8X/ipEJbMIsZzPhbe9trvFVDvz7ylZg1ylLpJunoBfIhVORUsdxoO9FwVD87gtmo70n/x3fulS6rtCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:44:02.453040Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.07198","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d4092b1ab69eccb56761b71201637b351d1b59aaecfe5c79598d20f50ab2f9a","sha256:1e923cd1836063e4822d4854a373db4a8b0d8725e4eb798d3871362d74fe3d56"],"state_sha256":"310891f3adde5915164a977dc26989c676b8c68c82112ac3d222cf67bff4f92e"}