{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KIVRZK7KTWDMGRUZRIPQVESAT7","short_pith_number":"pith:KIVRZK7K","schema_version":"1.0","canonical_sha256":"522b1cabea9d86c346998a1f0a92409fcffa957cdbd388b52b1c7f0801670405","source":{"kind":"arxiv","id":"2103.10897","version":3},"attestation_state":"computed","paper":{"title":"Bilinear Classes: A Structural Framework for Provable Generalization in RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gaurav Mahajan, Jason D. Lee, Ruosong Wang, Shachar Lovett, Sham M. Kakade, Simon S. Du, Wen Sun","submitted_at":"2021-03-19T16:34:20Z","abstract_excerpt":"This work introduces Bilinear Classes, a new structural framework, which permit generalization in reinforcement learning in a wide variety of settings through the use of function approximation. The framework incorporates nearly all existing models in which a polynomial sample complexity is achievable, and, notably, also includes new models, such as the Linear $Q^*/V^*$ model in which both the optimal $Q$-function and the optimal $V$-function are linear in some known feature space. Our main result provides an RL algorithm which has polynomial sample complexity for Bilinear Classes; notably, thi"},"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":"2103.10897","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-19T16:34:20Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"b3cb5072de7b019621db66ca9dd808393f36fe8db6bfbc36f183f87d7b606526","abstract_canon_sha256":"f1c56b0bbcc450dae8ea4e57f9ad7cd26c70278f6e8deadef8daad5ecfa2ba2e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:56:57.480035Z","signature_b64":"4QzXHHTiFwEowFwkVUaoiR1B00sNsUDuX4vGqUfWhrs+djf+a5LZTihvPqD94QHSHjylRlgg9CoL3jP1spvWDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"522b1cabea9d86c346998a1f0a92409fcffa957cdbd388b52b1c7f0801670405","last_reissued_at":"2026-07-05T02:56:57.479411Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:56:57.479411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bilinear Classes: A Structural Framework for Provable Generalization in RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gaurav Mahajan, Jason D. Lee, Ruosong Wang, Shachar Lovett, Sham M. Kakade, Simon S. Du, Wen Sun","submitted_at":"2021-03-19T16:34:20Z","abstract_excerpt":"This work introduces Bilinear Classes, a new structural framework, which permit generalization in reinforcement learning in a wide variety of settings through the use of function approximation. The framework incorporates nearly all existing models in which a polynomial sample complexity is achievable, and, notably, also includes new models, such as the Linear $Q^*/V^*$ model in which both the optimal $Q$-function and the optimal $V$-function are linear in some known feature space. Our main result provides an RL algorithm which has polynomial sample complexity for Bilinear Classes; notably, thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.10897","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2103.10897/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":"2103.10897","created_at":"2026-07-05T02:56:57.479502+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.10897v3","created_at":"2026-07-05T02:56:57.479502+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.10897","created_at":"2026-07-05T02:56:57.479502+00:00"},{"alias_kind":"pith_short_12","alias_value":"KIVRZK7KTWDM","created_at":"2026-07-05T02:56:57.479502+00:00"},{"alias_kind":"pith_short_16","alias_value":"KIVRZK7KTWDMGRUZ","created_at":"2026-07-05T02:56:57.479502+00:00"},{"alias_kind":"pith_short_8","alias_value":"KIVRZK7K","created_at":"2026-07-05T02:56:57.479502+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":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KIVRZK7KTWDMGRUZRIPQVESAT7","json":"https://pith.science/pith/KIVRZK7KTWDMGRUZRIPQVESAT7.json","graph_json":"https://pith.science/api/pith-number/KIVRZK7KTWDMGRUZRIPQVESAT7/graph.json","events_json":"https://pith.science/api/pith-number/KIVRZK7KTWDMGRUZRIPQVESAT7/events.json","paper":"https://pith.science/paper/KIVRZK7K"},"agent_actions":{"view_html":"https://pith.science/pith/KIVRZK7KTWDMGRUZRIPQVESAT7","download_json":"https://pith.science/pith/KIVRZK7KTWDMGRUZRIPQVESAT7.json","view_paper":"https://pith.science/paper/KIVRZK7K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.10897&json=true","fetch_graph":"https://pith.science/api/pith-number/KIVRZK7KTWDMGRUZRIPQVESAT7/graph.json","fetch_events":"https://pith.science/api/pith-number/KIVRZK7KTWDMGRUZRIPQVESAT7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KIVRZK7KTWDMGRUZRIPQVESAT7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KIVRZK7KTWDMGRUZRIPQVESAT7/action/storage_attestation","attest_author":"https://pith.science/pith/KIVRZK7KTWDMGRUZRIPQVESAT7/action/author_attestation","sign_citation":"https://pith.science/pith/KIVRZK7KTWDMGRUZRIPQVESAT7/action/citation_signature","submit_replication":"https://pith.science/pith/KIVRZK7KTWDMGRUZRIPQVESAT7/action/replication_record"}},"created_at":"2026-07-05T02:56:57.479502+00:00","updated_at":"2026-07-05T02:56:57.479502+00:00"}