{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ARMB6D3HFKFQTWNYOVHIFZEE26","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":"d6c59c48f2d9fcb0044300e90b00a139709821abf516bd1bcccf429e51fa5540","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-09T22:24:26Z","title_canon_sha256":"a70ddebb8694a1bd8c721519f6d30fcdf4c4f927ba33631f3de172301b0a60dd"},"schema_version":"1.0","source":{"id":"1812.03565","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.03565","created_at":"2026-05-17T23:54:53Z"},{"alias_kind":"arxiv_version","alias_value":"1812.03565v2","created_at":"2026-05-17T23:54:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.03565","created_at":"2026-05-17T23:54:53Z"},{"alias_kind":"pith_short_12","alias_value":"ARMB6D3HFKFQ","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"ARMB6D3HFKFQTWNY","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"ARMB6D3H","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:1e49f92532b96d2975b8cb1596dae27d38f28493ddae90a5208bffb5179eb285","target":"graph","created_at":"2026-05-17T23:54:53Z","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":"The effectiveness of model-based versus model-free methods is a long-standing question in reinforcement learning (RL). Motivated by recent empirical success of RL on continuous control tasks, we study the sample complexity of popular model-based and model-free algorithms on the Linear Quadratic Regulator (LQR). We show that for policy evaluation, a simple model-based plugin method requires asymptotically less samples than the classical least-squares temporal difference (LSTD) estimator to reach the same quality of solution; the sample complexity gap between the two methods can be at least a fa","authors_text":"Benjamin Recht, Stephen Tu","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-09T22:24:26Z","title":"The Gap Between Model-Based and Model-Free Methods on the Linear Quadratic Regulator: An Asymptotic Viewpoint"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.03565","kind":"arxiv","version":2},"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":"sha256:1d14e564db1d25a43bca8de87c2f01057f400082b2bd964e84c2e276dac6eeec","target":"record","created_at":"2026-05-17T23:54:53Z","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":"d6c59c48f2d9fcb0044300e90b00a139709821abf516bd1bcccf429e51fa5540","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-09T22:24:26Z","title_canon_sha256":"a70ddebb8694a1bd8c721519f6d30fcdf4c4f927ba33631f3de172301b0a60dd"},"schema_version":"1.0","source":{"id":"1812.03565","kind":"arxiv","version":2}},"canonical_sha256":"04581f0f672a8b09d9b8754e82e484d79ef81fd517b2451f16ef5adc9945769e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04581f0f672a8b09d9b8754e82e484d79ef81fd517b2451f16ef5adc9945769e","first_computed_at":"2026-05-17T23:54:53.299030Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:54:53.299030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l2+mL22ctSPuRvOls0Wwv3ixv7wRF6CeKX6HpQ1+BhH+8G1ytBg7Fb5ScwuQJmxyjjFQDwqYOjO1t+YwMTNWAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:54:53.299533Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.03565","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d14e564db1d25a43bca8de87c2f01057f400082b2bd964e84c2e276dac6eeec","sha256:1e49f92532b96d2975b8cb1596dae27d38f28493ddae90a5208bffb5179eb285"],"state_sha256":"4d6ff0e2b6c6aab11a3b53b624adb9d2a3e5ad881dd3cfb07882feb9266fc2bf"}