{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FVUPQBQHN4G5SSHWAGQDVG7BDX","short_pith_number":"pith:FVUPQBQH","schema_version":"1.0","canonical_sha256":"2d68f806076f0dd948f601a03a9be11de365c218d895e8518bfe69bee7713caa","source":{"kind":"arxiv","id":"2106.11612","version":2},"attestation_state":"computed","paper":{"title":"Uniform-PAC Bounds for Reinforcement Learning with Linear Function Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dongruo Zhou, Jiafan He, Quanquan Gu","submitted_at":"2021-06-22T08:48:56Z","abstract_excerpt":"We study reinforcement learning (RL) with linear function approximation. Existing algorithms for this problem only have high-probability regret and/or Probably Approximately Correct (PAC) sample complexity guarantees, which cannot guarantee the convergence to the optimal policy. In this paper, in order to overcome the limitation of existing algorithms, we propose a new algorithm called FLUTE, which enjoys uniform-PAC convergence to the optimal policy with high probability. The uniform-PAC guarantee is the strongest possible guarantee for reinforcement learning in the literature, which can dire"},"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":"2106.11612","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-22T08:48:56Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"ac5a50bd4c8c4be2583392cd65f7d9b625be80bcb780934db497e62d99fc3c8c","abstract_canon_sha256":"a3d7d346e6c78dddc43c1b047fd886b20a3ebcf57eab59779ec1cb2e427af82f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:44:45.007414Z","signature_b64":"/2FxANgdeLKwhhBFuRRnObWqui4B98Xu0LjwRHR6tz2qxrcuhRvPcygDSL+OIZdFKjFeGC2nYaiUH3N5QivJAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d68f806076f0dd948f601a03a9be11de365c218d895e8518bfe69bee7713caa","last_reissued_at":"2026-07-05T03:44:45.006910Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:44:45.006910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uniform-PAC Bounds for Reinforcement Learning with Linear Function Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dongruo Zhou, Jiafan He, Quanquan Gu","submitted_at":"2021-06-22T08:48:56Z","abstract_excerpt":"We study reinforcement learning (RL) with linear function approximation. Existing algorithms for this problem only have high-probability regret and/or Probably Approximately Correct (PAC) sample complexity guarantees, which cannot guarantee the convergence to the optimal policy. In this paper, in order to overcome the limitation of existing algorithms, we propose a new algorithm called FLUTE, which enjoys uniform-PAC convergence to the optimal policy with high probability. The uniform-PAC guarantee is the strongest possible guarantee for reinforcement learning in the literature, which can dire"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.11612","kind":"arxiv","version":2},"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/2106.11612/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2106.11612","created_at":"2026-07-05T03:44:45.006970+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.11612v2","created_at":"2026-07-05T03:44:45.006970+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.11612","created_at":"2026-07-05T03:44:45.006970+00:00"},{"alias_kind":"pith_short_12","alias_value":"FVUPQBQHN4G5","created_at":"2026-07-05T03:44:45.006970+00:00"},{"alias_kind":"pith_short_16","alias_value":"FVUPQBQHN4G5SSHW","created_at":"2026-07-05T03:44:45.006970+00:00"},{"alias_kind":"pith_short_8","alias_value":"FVUPQBQH","created_at":"2026-07-05T03:44:45.006970+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FVUPQBQHN4G5SSHWAGQDVG7BDX","json":"https://pith.science/pith/FVUPQBQHN4G5SSHWAGQDVG7BDX.json","graph_json":"https://pith.science/api/pith-number/FVUPQBQHN4G5SSHWAGQDVG7BDX/graph.json","events_json":"https://pith.science/api/pith-number/FVUPQBQHN4G5SSHWAGQDVG7BDX/events.json","paper":"https://pith.science/paper/FVUPQBQH"},"agent_actions":{"view_html":"https://pith.science/pith/FVUPQBQHN4G5SSHWAGQDVG7BDX","download_json":"https://pith.science/pith/FVUPQBQHN4G5SSHWAGQDVG7BDX.json","view_paper":"https://pith.science/paper/FVUPQBQH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.11612&json=true","fetch_graph":"https://pith.science/api/pith-number/FVUPQBQHN4G5SSHWAGQDVG7BDX/graph.json","fetch_events":"https://pith.science/api/pith-number/FVUPQBQHN4G5SSHWAGQDVG7BDX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FVUPQBQHN4G5SSHWAGQDVG7BDX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FVUPQBQHN4G5SSHWAGQDVG7BDX/action/storage_attestation","attest_author":"https://pith.science/pith/FVUPQBQHN4G5SSHWAGQDVG7BDX/action/author_attestation","sign_citation":"https://pith.science/pith/FVUPQBQHN4G5SSHWAGQDVG7BDX/action/citation_signature","submit_replication":"https://pith.science/pith/FVUPQBQHN4G5SSHWAGQDVG7BDX/action/replication_record"}},"created_at":"2026-07-05T03:44:45.006970+00:00","updated_at":"2026-07-05T03:44:45.006970+00:00"}