{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:A4LEWSSWR2KLP773HXX4GQM6Q7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"50c752108716f889bac733b9c96af8b1cafb4b38e41993e1f69c52d2e526cab4","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-30T17:59:16Z","title_canon_sha256":"7f182231176213b2b1064786d9350195295371de90f7dee974cd8834cfe242f5"},"schema_version":"1.0","source":{"id":"2209.15634","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.15634","created_at":"2026-07-05T05:02:21Z"},{"alias_kind":"arxiv_version","alias_value":"2209.15634v1","created_at":"2026-07-05T05:02:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.15634","created_at":"2026-07-05T05:02:21Z"},{"alias_kind":"pith_short_12","alias_value":"A4LEWSSWR2KL","created_at":"2026-07-05T05:02:21Z"},{"alias_kind":"pith_short_16","alias_value":"A4LEWSSWR2KLP773","created_at":"2026-07-05T05:02:21Z"},{"alias_kind":"pith_short_8","alias_value":"A4LEWSSW","created_at":"2026-07-05T05:02:21Z"}],"graph_snapshots":[{"event_id":"sha256:efabe120f008b970d7135c15350fcabd99a7b0cdbf3cde90bd3b3222c5043536","target":"graph","created_at":"2026-07-05T05:02:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2209.15634/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Angela Yuan, Chris Junchi Li, Michael I. Jordan, Quanquan Gu, Zixiang Chen","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-30T17:59:16Z","title":"A General Framework for Sample-Efficient Function Approximation in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.15634","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:56ae29d16347933623b0ca9b2fe7652c806e04be0d23f7dee7a72756e7f2611f","target":"record","created_at":"2026-07-05T05:02:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"50c752108716f889bac733b9c96af8b1cafb4b38e41993e1f69c52d2e526cab4","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-30T17:59:16Z","title_canon_sha256":"7f182231176213b2b1064786d9350195295371de90f7dee974cd8834cfe242f5"},"schema_version":"1.0","source":{"id":"2209.15634","kind":"arxiv","version":1}},"canonical_sha256":"07164b4a568e94b7fffb3defc3419e87df88952c05b89daf3ea848a4d1107a36","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"07164b4a568e94b7fffb3defc3419e87df88952c05b89daf3ea848a4d1107a36","first_computed_at":"2026-07-05T05:02:21.808687Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:02:21.808687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A+F5M1VXLOYZlplZ2CF5KrL3z5KrWnxZtzeYaF/oAvkGYUKUexYyrCi+TlPtlF88cR3GbnqighW+6tEGm/mFDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:02:21.809080Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.15634","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:56ae29d16347933623b0ca9b2fe7652c806e04be0d23f7dee7a72756e7f2611f","sha256:efabe120f008b970d7135c15350fcabd99a7b0cdbf3cde90bd3b3222c5043536"],"state_sha256":"3a0c86a5aa8c03f05b7a3fc1d5a8d422552ef8e6f8e32fb038ec4e8339661c54"}