{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:3VCUT2ESLVSS36BRNLEWYBHZ34","short_pith_number":"pith:3VCUT2ES","schema_version":"1.0","canonical_sha256":"dd4549e8925d652df8316ac96c04f9df289201a3325a301cb58183c7d532c531","source":{"kind":"arxiv","id":"1703.07710","version":3},"attestation_state":"computed","paper":{"title":"Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christoph Dann, Emma Brunskill, Tor Lattimore","submitted_at":"2017-03-22T15:34:23Z","abstract_excerpt":"Statistical performance bounds for reinforcement learning (RL) algorithms can be critical for high-stakes applications like healthcare. This paper introduces a new framework for theoretically measuring the performance of such algorithms called Uniform-PAC, which is a strengthening of the classical Probably Approximately Correct (PAC) framework. In contrast to the PAC framework, the uniform version may be used to derive high probability regret guarantees and so forms a bridge between the two setups that has been missing in the literature. We demonstrate the benefits of the new framework for fin"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1703.07710","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-22T15:34:23Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"e13c3f9f433c674c6938dc861e4d11ae34f1e40b43253ecf14c8298f1b9ddf4d","abstract_canon_sha256":"54956bf1f931434a8708c76f33c73934925e3ca4993f01aee2e1456b10c1275c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:26:57.467769Z","signature_b64":"NjbyjvXUshxnQGZxCuJhrI4qQs78ulwlg48/5ltzpEDzHVVf6LTuF8vX0r6ilZIesr3C5+XHGWfruMjFy8JxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd4549e8925d652df8316ac96c04f9df289201a3325a301cb58183c7d532c531","last_reissued_at":"2026-05-18T00:26:57.467251Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:26:57.467251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christoph Dann, Emma Brunskill, Tor Lattimore","submitted_at":"2017-03-22T15:34:23Z","abstract_excerpt":"Statistical performance bounds for reinforcement learning (RL) algorithms can be critical for high-stakes applications like healthcare. This paper introduces a new framework for theoretically measuring the performance of such algorithms called Uniform-PAC, which is a strengthening of the classical Probably Approximately Correct (PAC) framework. In contrast to the PAC framework, the uniform version may be used to derive high probability regret guarantees and so forms a bridge between the two setups that has been missing in the literature. We demonstrate the benefits of the new framework for fin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.07710","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":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1703.07710","created_at":"2026-05-18T00:26:57.467331+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.07710v3","created_at":"2026-05-18T00:26:57.467331+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.07710","created_at":"2026-05-18T00:26:57.467331+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01242","citing_title":"Breaking the Computational Barrier: Provably Efficient Actor-Critic for Low-Rank MDPs","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3VCUT2ESLVSS36BRNLEWYBHZ34","json":"https://pith.science/pith/3VCUT2ESLVSS36BRNLEWYBHZ34.json","graph_json":"https://pith.science/api/pith-number/3VCUT2ESLVSS36BRNLEWYBHZ34/graph.json","events_json":"https://pith.science/api/pith-number/3VCUT2ESLVSS36BRNLEWYBHZ34/events.json","paper":"https://pith.science/paper/3VCUT2ES"},"agent_actions":{"view_html":"https://pith.science/pith/3VCUT2ESLVSS36BRNLEWYBHZ34","download_json":"https://pith.science/pith/3VCUT2ESLVSS36BRNLEWYBHZ34.json","view_paper":"https://pith.science/paper/3VCUT2ES","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.07710&json=true","fetch_graph":"https://pith.science/api/pith-number/3VCUT2ESLVSS36BRNLEWYBHZ34/graph.json","fetch_events":"https://pith.science/api/pith-number/3VCUT2ESLVSS36BRNLEWYBHZ34/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3VCUT2ESLVSS36BRNLEWYBHZ34/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3VCUT2ESLVSS36BRNLEWYBHZ34/action/storage_attestation","attest_author":"https://pith.science/pith/3VCUT2ESLVSS36BRNLEWYBHZ34/action/author_attestation","sign_citation":"https://pith.science/pith/3VCUT2ESLVSS36BRNLEWYBHZ34/action/citation_signature","submit_replication":"https://pith.science/pith/3VCUT2ESLVSS36BRNLEWYBHZ34/action/replication_record"}},"created_at":"2026-05-18T00:26:57.467331+00:00","updated_at":"2026-05-18T00:26:57.467331+00:00"}