{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:UPB2SMXDIGQEZTYRNMANQOQ56P","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":"7ca1ddbab311c560e416ccdd4f37036c053bb0ba11654ef38dd1eac21eb86d30","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-10T17:21:35Z","title_canon_sha256":"28d6e70b6d86842ebbbf836f906eb638cdd209923328aaa3ab448cbf593bd028"},"schema_version":"1.0","source":{"id":"1807.03765","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.03765","created_at":"2026-05-18T00:11:01Z"},{"alias_kind":"arxiv_version","alias_value":"1807.03765v1","created_at":"2026-05-18T00:11:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.03765","created_at":"2026-05-18T00:11:01Z"},{"alias_kind":"pith_short_12","alias_value":"UPB2SMXDIGQE","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UPB2SMXDIGQEZTYR","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UPB2SMXD","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:ba292708f88e0b57f2cb32032802fbf2b58a6fd1df3bb9791aa2d442106632cc","target":"graph","created_at":"2026-05-18T00:11:01Z","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"},"paper":{"abstract_excerpt":"Model-free reinforcement learning (RL) algorithms, such as Q-learning, directly parameterize and update value functions or policies without explicitly modeling the environment. They are typically simpler, more flexible to use, and thus more prevalent in modern deep RL than model-based approaches. However, empirical work has suggested that model-free algorithms may require more samples to learn [Deisenroth and Rasmussen 2011, Schulman et al. 2015]. The theoretical question of \"whether model-free algorithms can be made sample efficient\" is one of the most fundamental questions in RL, and remains","authors_text":"Chi Jin, Michael I. Jordan, Sebastien Bubeck, Zeyuan Allen-Zhu","cross_cats":["cs.AI","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-10T17:21:35Z","title":"Is Q-learning Provably Efficient?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.03765","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":"sha256:27340dee04423f18bc4706d7527e34d5f7f419b04679d35f1f717c078f986bcb","target":"record","created_at":"2026-05-18T00:11:01Z","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":"7ca1ddbab311c560e416ccdd4f37036c053bb0ba11654ef38dd1eac21eb86d30","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-10T17:21:35Z","title_canon_sha256":"28d6e70b6d86842ebbbf836f906eb638cdd209923328aaa3ab448cbf593bd028"},"schema_version":"1.0","source":{"id":"1807.03765","kind":"arxiv","version":1}},"canonical_sha256":"a3c3a932e341a04ccf116b00d83a1df3ff16fa03952aca3acd48711c007d90b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3c3a932e341a04ccf116b00d83a1df3ff16fa03952aca3acd48711c007d90b6","first_computed_at":"2026-05-18T00:11:01.012279Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:11:01.012279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vvF1N5CI6sPKO+R+MYrrxLPM0A977lrgUQfW7NwKNBriUvRRM4DsiBC3/4RKIwtnYiK1UiobTxTijfHEvw8fCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:11:01.013083Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.03765","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27340dee04423f18bc4706d7527e34d5f7f419b04679d35f1f717c078f986bcb","sha256:ba292708f88e0b57f2cb32032802fbf2b58a6fd1df3bb9791aa2d442106632cc"],"state_sha256":"3b8f3b2f041ef10c1cd4c2276bf63f6308afa2682a4bf6725bb20220742687fc"}