{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:5225D37VPNIMBVLMHXYVOR22HX","short_pith_number":"pith:5225D37V","schema_version":"1.0","canonical_sha256":"eeb5d1eff57b50c0d56c3df157475a3dd1d032326c996d75b0c70d154fff559d","source":{"kind":"arxiv","id":"1802.09081","version":2},"attestation_state":"computed","paper":{"title":"Temporal Difference Models: Model-Free Deep RL for Model-Based Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Murtaza Dalal, Sergey Levine, Shixiang Gu, Vitchyr Pong","submitted_at":"2018-02-25T21:14:44Z","abstract_excerpt":"Model-free reinforcement learning (RL) is a powerful, general tool for learning complex behaviors. However, its sample efficiency is often impractically large for solving challenging real-world problems, even with off-policy algorithms such as Q-learning. A limiting factor in classic model-free RL is that the learning signal consists only of scalar rewards, ignoring much of the rich information contained in state transition tuples. Model-based RL uses this information, by training a predictive model, but often does not achieve the same asymptotic performance as model-free RL due to model bias."},"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":"1802.09081","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-25T21:14:44Z","cross_cats_sorted":[],"title_canon_sha256":"c4beaa4f62a1117d8bcf04072b688b1dbfae93dfa97ef68b94e8425ae634d867","abstract_canon_sha256":"5ac7d2b91d911dfd2f770f877dabc6eef6d1342362be58a7b3c0e43d63ea9ac3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:42:57.946078Z","signature_b64":"iEnI84ilsm5dCD81L8gvOCl48QIfKD6UA5t3h+N3mRhRkHB7KT8hIIlnNXXlofwNuCF/+Go7QUsj4jhG/LXzBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eeb5d1eff57b50c0d56c3df157475a3dd1d032326c996d75b0c70d154fff559d","last_reissued_at":"2026-07-05T00:42:57.945600Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:42:57.945600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Temporal Difference Models: Model-Free Deep RL for Model-Based Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Murtaza Dalal, Sergey Levine, Shixiang Gu, Vitchyr Pong","submitted_at":"2018-02-25T21:14:44Z","abstract_excerpt":"Model-free reinforcement learning (RL) is a powerful, general tool for learning complex behaviors. However, its sample efficiency is often impractically large for solving challenging real-world problems, even with off-policy algorithms such as Q-learning. A limiting factor in classic model-free RL is that the learning signal consists only of scalar rewards, ignoring much of the rich information contained in state transition tuples. Model-based RL uses this information, by training a predictive model, but often does not achieve the same asymptotic performance as model-free RL due to model bias."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.09081","kind":"arxiv","version":2},"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/1802.09081/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":"1802.09081","created_at":"2026-07-05T00:42:57.945653+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.09081v2","created_at":"2026-07-05T00:42:57.945653+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.09081","created_at":"2026-07-05T00:42:57.945653+00:00"},{"alias_kind":"pith_short_12","alias_value":"5225D37VPNIM","created_at":"2026-07-05T00:42:57.945653+00:00"},{"alias_kind":"pith_short_16","alias_value":"5225D37VPNIMBVLM","created_at":"2026-07-05T00:42:57.945653+00:00"},{"alias_kind":"pith_short_8","alias_value":"5225D37V","created_at":"2026-07-05T00:42:57.945653+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09476","citing_title":"Goal Sets, Not Goal States: Queryable Robot Goals through Goal-Set Hindsight Relabeling","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06145","citing_title":"Unifying Goal-Conditioned RL and Unsupervised Skill Learning via Control-Maximization","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01862","citing_title":"QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL","ref_index":146,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5225D37VPNIMBVLMHXYVOR22HX","json":"https://pith.science/pith/5225D37VPNIMBVLMHXYVOR22HX.json","graph_json":"https://pith.science/api/pith-number/5225D37VPNIMBVLMHXYVOR22HX/graph.json","events_json":"https://pith.science/api/pith-number/5225D37VPNIMBVLMHXYVOR22HX/events.json","paper":"https://pith.science/paper/5225D37V"},"agent_actions":{"view_html":"https://pith.science/pith/5225D37VPNIMBVLMHXYVOR22HX","download_json":"https://pith.science/pith/5225D37VPNIMBVLMHXYVOR22HX.json","view_paper":"https://pith.science/paper/5225D37V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.09081&json=true","fetch_graph":"https://pith.science/api/pith-number/5225D37VPNIMBVLMHXYVOR22HX/graph.json","fetch_events":"https://pith.science/api/pith-number/5225D37VPNIMBVLMHXYVOR22HX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5225D37VPNIMBVLMHXYVOR22HX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5225D37VPNIMBVLMHXYVOR22HX/action/storage_attestation","attest_author":"https://pith.science/pith/5225D37VPNIMBVLMHXYVOR22HX/action/author_attestation","sign_citation":"https://pith.science/pith/5225D37VPNIMBVLMHXYVOR22HX/action/citation_signature","submit_replication":"https://pith.science/pith/5225D37VPNIMBVLMHXYVOR22HX/action/replication_record"}},"created_at":"2026-07-05T00:42:57.945653+00:00","updated_at":"2026-07-05T00:42:57.945653+00:00"}