{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:TSMUN3OI6D2YHKT254BDTBX47P","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":"4b37d51fcb66581002f1624a425a8c21830bc8922452af5199e1417cb0ae2246","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-01T21:17:21Z","title_canon_sha256":"9f0fad8a81eec0fabd17ce94701d2e7c8be50b3f241c16053297799256e430f2"},"schema_version":"1.0","source":{"id":"1901.00210","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.00210","created_at":"2026-07-05T00:16:32Z"},{"alias_kind":"arxiv_version","alias_value":"1901.00210v4","created_at":"2026-07-05T00:16:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.00210","created_at":"2026-07-05T00:16:32Z"},{"alias_kind":"pith_short_12","alias_value":"TSMUN3OI6D2Y","created_at":"2026-07-05T00:16:32Z"},{"alias_kind":"pith_short_16","alias_value":"TSMUN3OI6D2YHKT2","created_at":"2026-07-05T00:16:32Z"},{"alias_kind":"pith_short_8","alias_value":"TSMUN3OI","created_at":"2026-07-05T00:16:32Z"}],"graph_snapshots":[{"event_id":"sha256:f107bb05a477456975aa64ca74ba4c5ee20451b9f735c2aec43dce8dd2b5f83f","target":"graph","created_at":"2026-07-05T00:16:32Z","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/1901.00210/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Strong worst-case performance bounds for episodic reinforcement learning exist but fortunately in practice RL algorithms perform much better than such bounds would predict. Algorithms and theory that provide strong problem-dependent bounds could help illuminate the key features of what makes a RL problem hard and reduce the barrier to using RL algorithms in practice. As a step towards this we derive an algorithm for finite horizon discrete MDPs and associated analysis that both yields state-of-the art worst-case regret bounds in the dominant terms and yields substantially tighter bounds if the","authors_text":"Andrea Zanette, Emma Brunskill","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-01T21:17:21Z","title":"Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function Bounds"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.00210","kind":"arxiv","version":4},"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":"sha256:1be9f71d0321dcc06d087b0b8d83782b7bb1fad6f574279e257c194dcfb4128e","target":"record","created_at":"2026-07-05T00:16:32Z","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":"4b37d51fcb66581002f1624a425a8c21830bc8922452af5199e1417cb0ae2246","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-01T21:17:21Z","title_canon_sha256":"9f0fad8a81eec0fabd17ce94701d2e7c8be50b3f241c16053297799256e430f2"},"schema_version":"1.0","source":{"id":"1901.00210","kind":"arxiv","version":4}},"canonical_sha256":"9c9946edc8f0f583aa7aef023986fcfbda5f1443673dc92515a7ac212051bd4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c9946edc8f0f583aa7aef023986fcfbda5f1443673dc92515a7ac212051bd4d","first_computed_at":"2026-07-05T00:16:32.251159Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:16:32.251159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vo93d2hf3H+ZQrYx04W+1JQDLmDRUYAwfGz+2Rv3qG7W6ubCEdTab9MhNJkwoLlvvUuZZDT84PlfmbbgPtNXCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:16:32.251509Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.00210","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1be9f71d0321dcc06d087b0b8d83782b7bb1fad6f574279e257c194dcfb4128e","sha256:f107bb05a477456975aa64ca74ba4c5ee20451b9f735c2aec43dce8dd2b5f83f"],"state_sha256":"5d115309e5d1595d8697d8fcb8c0e48455e50ad974707eafc46129fcaecd61aa"}