{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ZOYZQV7OOAN4M4I3Q2QWGBUT7G","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":"0305bec0d09402132b0d371f7acb556a189f6c6f8859d0467b2ea7be20a03323","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-14T06:17:49Z","title_canon_sha256":"97a06154461f493b3448f3739f53faee29423ece65f11e109525c7af7dd9a121"},"schema_version":"1.0","source":{"id":"1910.05927","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.05927","created_at":"2026-07-05T01:33:17Z"},{"alias_kind":"arxiv_version","alias_value":"1910.05927v3","created_at":"2026-07-05T01:33:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.05927","created_at":"2026-07-05T01:33:17Z"},{"alias_kind":"pith_short_12","alias_value":"ZOYZQV7OOAN4","created_at":"2026-07-05T01:33:17Z"},{"alias_kind":"pith_short_16","alias_value":"ZOYZQV7OOAN4M4I3","created_at":"2026-07-05T01:33:17Z"},{"alias_kind":"pith_short_8","alias_value":"ZOYZQV7O","created_at":"2026-07-05T01:33:17Z"}],"graph_snapshots":[{"event_id":"sha256:a2c1da56ca378e4ea8c87fcd5012117777d185d4a05263ef1a7053ea46420548","target":"graph","created_at":"2026-07-05T01:33:17Z","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/1910.05927/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We compare the model-free reinforcement learning with the model-based approaches through the lens of the expressive power of neural networks for policies, $Q$-functions, and dynamics. We show, theoretically and empirically, that even for one-dimensional continuous state space, there are many MDPs whose optimal $Q$-functions and policies are much more complex than the dynamics. We hypothesize many real-world MDPs also have a similar property. For these MDPs, model-based planning is a favorable algorithm, because the resulting policies can approximate the optimal policy significantly better than","authors_text":"Kefan Dong, Tengyu Ma, Yuping Luo","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-14T06:17:49Z","title":"On the Expressivity of Neural Networks for Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.05927","kind":"arxiv","version":3},"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":"sha256:17e655803993b8716bdaa3b76388489597eb7c3404f423557d59417975e87522","target":"record","created_at":"2026-07-05T01:33:17Z","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":"0305bec0d09402132b0d371f7acb556a189f6c6f8859d0467b2ea7be20a03323","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-14T06:17:49Z","title_canon_sha256":"97a06154461f493b3448f3739f53faee29423ece65f11e109525c7af7dd9a121"},"schema_version":"1.0","source":{"id":"1910.05927","kind":"arxiv","version":3}},"canonical_sha256":"cbb19857ee701bc6711b86a1630693f9bd0d64705056bea7592629ef7a739e9e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cbb19857ee701bc6711b86a1630693f9bd0d64705056bea7592629ef7a739e9e","first_computed_at":"2026-07-05T01:33:17.934173Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:33:17.934173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P1982yw/r2VNv2qOehxH5ZIO87nmQdYwTTtMfTEDC3LgQHEjpubSvoyxrXMqc0QtqoxxdLsl+/wA3NnOqCPsAw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:33:17.934579Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.05927","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:17e655803993b8716bdaa3b76388489597eb7c3404f423557d59417975e87522","sha256:a2c1da56ca378e4ea8c87fcd5012117777d185d4a05263ef1a7053ea46420548"],"state_sha256":"76c5f158b8454e4bf78046c2d0f3c9ea9a9fb35bafb9d97d011c6b968a1179b5"}