{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:A4LEWSSWR2KLP773HXX4GQM6Q7","short_pith_number":"pith:A4LEWSSW","schema_version":"1.0","canonical_sha256":"07164b4a568e94b7fffb3defc3419e87df88952c05b89daf3ea848a4d1107a36","source":{"kind":"arxiv","id":"2209.15634","version":1},"attestation_state":"computed","paper":{"title":"A General Framework for Sample-Efficient Function Approximation in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Angela Yuan, Chris Junchi Li, Michael I. Jordan, Quanquan Gu, Zixiang Chen","submitted_at":"2022-09-30T17:59:16Z","abstract_excerpt":"With the increasing need for handling large state and action spaces, general function approximation has become a key technique in reinforcement learning (RL). In this paper, we propose a general framework that unifies model-based and model-free RL, and an Admissible Bellman Characterization (ABC) class that subsumes nearly all Markov Decision Process (MDP) models in the literature for tractable RL. We propose a novel estimation function with decomposable structural properties for optimization-based exploration and the functional eluder dimension as a complexity measure of the ABC class. 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":"2209.15634","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-30T17:59:16Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"7f182231176213b2b1064786d9350195295371de90f7dee974cd8834cfe242f5","abstract_canon_sha256":"50c752108716f889bac733b9c96af8b1cafb4b38e41993e1f69c52d2e526cab4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:02:21.809080Z","signature_b64":"A+F5M1VXLOYZlplZ2CF5KrL3z5KrWnxZtzeYaF/oAvkGYUKUexYyrCi+TlPtlF88cR3GbnqighW+6tEGm/mFDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07164b4a568e94b7fffb3defc3419e87df88952c05b89daf3ea848a4d1107a36","last_reissued_at":"2026-07-05T05:02:21.808687Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:02:21.808687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A General Framework for Sample-Efficient Function Approximation in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Angela Yuan, Chris Junchi Li, Michael I. Jordan, Quanquan Gu, Zixiang Chen","submitted_at":"2022-09-30T17:59:16Z","abstract_excerpt":"With the increasing need for handling large state and action spaces, general function approximation has become a key technique in reinforcement learning (RL). In this paper, we propose a general framework that unifies model-based and model-free RL, and an Admissible Bellman Characterization (ABC) class that subsumes nearly all Markov Decision Process (MDP) models in the literature for tractable RL. We propose a novel estimation function with decomposable structural properties for optimization-based exploration and the functional eluder dimension as a complexity measure of the ABC class. Under "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.15634","kind":"arxiv","version":1},"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/2209.15634/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":"2209.15634","created_at":"2026-07-05T05:02:21.808749+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.15634v1","created_at":"2026-07-05T05:02:21.808749+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.15634","created_at":"2026-07-05T05:02:21.808749+00:00"},{"alias_kind":"pith_short_12","alias_value":"A4LEWSSWR2KL","created_at":"2026-07-05T05:02:21.808749+00:00"},{"alias_kind":"pith_short_16","alias_value":"A4LEWSSWR2KLP773","created_at":"2026-07-05T05:02:21.808749+00:00"},{"alias_kind":"pith_short_8","alias_value":"A4LEWSSW","created_at":"2026-07-05T05:02:21.808749+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.13966","citing_title":"Provably Efficient Offline-to-Online Value Adaptation with General Function Approximation","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A4LEWSSWR2KLP773HXX4GQM6Q7","json":"https://pith.science/pith/A4LEWSSWR2KLP773HXX4GQM6Q7.json","graph_json":"https://pith.science/api/pith-number/A4LEWSSWR2KLP773HXX4GQM6Q7/graph.json","events_json":"https://pith.science/api/pith-number/A4LEWSSWR2KLP773HXX4GQM6Q7/events.json","paper":"https://pith.science/paper/A4LEWSSW"},"agent_actions":{"view_html":"https://pith.science/pith/A4LEWSSWR2KLP773HXX4GQM6Q7","download_json":"https://pith.science/pith/A4LEWSSWR2KLP773HXX4GQM6Q7.json","view_paper":"https://pith.science/paper/A4LEWSSW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.15634&json=true","fetch_graph":"https://pith.science/api/pith-number/A4LEWSSWR2KLP773HXX4GQM6Q7/graph.json","fetch_events":"https://pith.science/api/pith-number/A4LEWSSWR2KLP773HXX4GQM6Q7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A4LEWSSWR2KLP773HXX4GQM6Q7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A4LEWSSWR2KLP773HXX4GQM6Q7/action/storage_attestation","attest_author":"https://pith.science/pith/A4LEWSSWR2KLP773HXX4GQM6Q7/action/author_attestation","sign_citation":"https://pith.science/pith/A4LEWSSWR2KLP773HXX4GQM6Q7/action/citation_signature","submit_replication":"https://pith.science/pith/A4LEWSSWR2KLP773HXX4GQM6Q7/action/replication_record"}},"created_at":"2026-07-05T05:02:21.808749+00:00","updated_at":"2026-07-05T05:02:21.808749+00:00"}