{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:C4OARQPNY27FXDIPLYK4W3OCII","short_pith_number":"pith:C4OARQPN","schema_version":"1.0","canonical_sha256":"171c08c1edc6be5b8d0f5e15cb6dc24226340304ac8955dccd4e708970ee4cc0","source":{"kind":"arxiv","id":"2107.06466","version":2},"attestation_state":"computed","paper":{"title":"Going Beyond Linear RL: Sample Efficient Neural Function Approximation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Baihe Huang, Jason D. Lee, Jiaqi Yang, Kaixuan Huang, Qi Lei, Runzhe Wang, Sham M. Kakade","submitted_at":"2021-07-14T03:03:56Z","abstract_excerpt":"Deep Reinforcement Learning (RL) powered by neural net approximation of the Q function has had enormous empirical success. While the theory of RL has traditionally focused on linear function approximation (or eluder dimension) approaches, little is known about nonlinear RL with neural net approximations of the Q functions. This is the focus of this work, where we study function approximation with two-layer neural networks (considering both ReLU and polynomial activation functions). Our first result is a computationally and statistically efficient algorithm in the generative model setting under"},"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":"2107.06466","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-14T03:03:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"331dfb76b0fe483563ad0712aca09c393299d5509597105fbbfffab5151f4a1f","abstract_canon_sha256":"63cece5059fcfb7c5589314112f8ebe5fc8ccaae25b349dbf4a786d8213889fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:43:42.647209Z","signature_b64":"WvppOT20S7L588+94UZVLmrbVjJEwotsZQI5qTi0MQxcqLAmGvc1aISBkf2F6xi/Qr1gXkQZ5aNV2BnfeaPaBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"171c08c1edc6be5b8d0f5e15cb6dc24226340304ac8955dccd4e708970ee4cc0","last_reissued_at":"2026-07-05T03:43:42.646783Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:43:42.646783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Going Beyond Linear RL: Sample Efficient Neural Function Approximation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Baihe Huang, Jason D. Lee, Jiaqi Yang, Kaixuan Huang, Qi Lei, Runzhe Wang, Sham M. Kakade","submitted_at":"2021-07-14T03:03:56Z","abstract_excerpt":"Deep Reinforcement Learning (RL) powered by neural net approximation of the Q function has had enormous empirical success. While the theory of RL has traditionally focused on linear function approximation (or eluder dimension) approaches, little is known about nonlinear RL with neural net approximations of the Q functions. This is the focus of this work, where we study function approximation with two-layer neural networks (considering both ReLU and polynomial activation functions). Our first result is a computationally and statistically efficient algorithm in the generative model setting under"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.06466","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/2107.06466/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":"2107.06466","created_at":"2026-07-05T03:43:42.646841+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.06466v2","created_at":"2026-07-05T03:43:42.646841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.06466","created_at":"2026-07-05T03:43:42.646841+00:00"},{"alias_kind":"pith_short_12","alias_value":"C4OARQPNY27F","created_at":"2026-07-05T03:43:42.646841+00:00"},{"alias_kind":"pith_short_16","alias_value":"C4OARQPNY27FXDIP","created_at":"2026-07-05T03:43:42.646841+00:00"},{"alias_kind":"pith_short_8","alias_value":"C4OARQPN","created_at":"2026-07-05T03:43:42.646841+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/C4OARQPNY27FXDIPLYK4W3OCII","json":"https://pith.science/pith/C4OARQPNY27FXDIPLYK4W3OCII.json","graph_json":"https://pith.science/api/pith-number/C4OARQPNY27FXDIPLYK4W3OCII/graph.json","events_json":"https://pith.science/api/pith-number/C4OARQPNY27FXDIPLYK4W3OCII/events.json","paper":"https://pith.science/paper/C4OARQPN"},"agent_actions":{"view_html":"https://pith.science/pith/C4OARQPNY27FXDIPLYK4W3OCII","download_json":"https://pith.science/pith/C4OARQPNY27FXDIPLYK4W3OCII.json","view_paper":"https://pith.science/paper/C4OARQPN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.06466&json=true","fetch_graph":"https://pith.science/api/pith-number/C4OARQPNY27FXDIPLYK4W3OCII/graph.json","fetch_events":"https://pith.science/api/pith-number/C4OARQPNY27FXDIPLYK4W3OCII/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C4OARQPNY27FXDIPLYK4W3OCII/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C4OARQPNY27FXDIPLYK4W3OCII/action/storage_attestation","attest_author":"https://pith.science/pith/C4OARQPNY27FXDIPLYK4W3OCII/action/author_attestation","sign_citation":"https://pith.science/pith/C4OARQPNY27FXDIPLYK4W3OCII/action/citation_signature","submit_replication":"https://pith.science/pith/C4OARQPNY27FXDIPLYK4W3OCII/action/replication_record"}},"created_at":"2026-07-05T03:43:42.646841+00:00","updated_at":"2026-07-05T03:43:42.646841+00:00"}