{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VY7FCRDP46K4SW3Z7ULAUOBAYT","short_pith_number":"pith:VY7FCRDP","schema_version":"1.0","canonical_sha256":"ae3e51446fe795c95b79fd160a3820c4c5e58c2e084ddaafdd93305c85e8a581","source":{"kind":"arxiv","id":"1803.00101","version":1},"attestation_state":"computed","paper":{"title":"Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alvin Wan, Ion Stoica, Joseph E. Gonzalez, Michael I. Jordan, Sergey Levine, Vladimir Feinberg","submitted_at":"2018-02-28T21:43:37Z","abstract_excerpt":"Recent model-free reinforcement learning algorithms have proposed incorporating learned dynamics models as a source of additional data with the intention of reducing sample complexity. Such methods hold the promise of incorporating imagined data coupled with a notion of model uncertainty to accelerate the learning of continuous control tasks. Unfortunately, they rely on heuristics that limit usage of the dynamics model. We present model-based value expansion, which controls for uncertainty in the model by only allowing imagination to fixed depth. By enabling wider use of learned dynamics model"},"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":"1803.00101","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-02-28T21:43:37Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"9cfe089cf9b590544fd6f5de162aa5377ef9ace753cccccb0d05faac29e491df","abstract_canon_sha256":"a39856f72d9632ee711dc4dd0008b4bbd4b0d86e77abb046edaa1bd3d9d43146"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:13.342784Z","signature_b64":"wYzQa140mmg0p9ODEp+oIIXrxQutk4pFwA+ymLETpKaEQGYFowncIVqpsm/8qHaK0PpPbxE0Zq7Qik+2PC2sDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae3e51446fe795c95b79fd160a3820c4c5e58c2e084ddaafdd93305c85e8a581","last_reissued_at":"2026-05-18T00:22:13.342163Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:13.342163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alvin Wan, Ion Stoica, Joseph E. Gonzalez, Michael I. Jordan, Sergey Levine, Vladimir Feinberg","submitted_at":"2018-02-28T21:43:37Z","abstract_excerpt":"Recent model-free reinforcement learning algorithms have proposed incorporating learned dynamics models as a source of additional data with the intention of reducing sample complexity. Such methods hold the promise of incorporating imagined data coupled with a notion of model uncertainty to accelerate the learning of continuous control tasks. Unfortunately, they rely on heuristics that limit usage of the dynamics model. We present model-based value expansion, which controls for uncertainty in the model by only allowing imagination to fixed depth. By enabling wider use of learned dynamics model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.00101","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1803.00101","created_at":"2026-05-18T00:22:13.342238+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.00101v1","created_at":"2026-05-18T00:22:13.342238+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.00101","created_at":"2026-05-18T00:22:13.342238+00:00"},{"alias_kind":"pith_short_12","alias_value":"VY7FCRDP46K4","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"VY7FCRDP46K4SW3Z","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"VY7FCRDP","created_at":"2026-05-18T12:32:59.047623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"1906.08649","citing_title":"Exploring Model-based Planning with Policy Networks","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2502.05907","citing_title":"EvolvingAgent: Curriculum Self-evolving Agent with Continual World Model for Long-Horizon Tasks","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2510.04280","citing_title":"A KL-regularization Framework for Learning to Plan with Adaptive Priors","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16692","citing_title":"EfficientTDMPC: Improved MPC Objectives for Sample-Efficient Continuous Control","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2509.19538","citing_title":"DAWM: Diffusion Action World Models for Offline Reinforcement Learning via Action-Inferred Transitions","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09808","citing_title":"Quantifying the Utility of User Simulators for Building Collaborative LLM Assistants","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"1912.01603","citing_title":"Dream to Control: Learning Behaviors by Latent Imagination","ref_index":14,"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":120,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04401","citing_title":"ReinVBC: A Model-based Reinforcement Learning Approach to Vehicle Braking Controller","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VY7FCRDP46K4SW3Z7ULAUOBAYT","json":"https://pith.science/pith/VY7FCRDP46K4SW3Z7ULAUOBAYT.json","graph_json":"https://pith.science/api/pith-number/VY7FCRDP46K4SW3Z7ULAUOBAYT/graph.json","events_json":"https://pith.science/api/pith-number/VY7FCRDP46K4SW3Z7ULAUOBAYT/events.json","paper":"https://pith.science/paper/VY7FCRDP"},"agent_actions":{"view_html":"https://pith.science/pith/VY7FCRDP46K4SW3Z7ULAUOBAYT","download_json":"https://pith.science/pith/VY7FCRDP46K4SW3Z7ULAUOBAYT.json","view_paper":"https://pith.science/paper/VY7FCRDP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.00101&json=true","fetch_graph":"https://pith.science/api/pith-number/VY7FCRDP46K4SW3Z7ULAUOBAYT/graph.json","fetch_events":"https://pith.science/api/pith-number/VY7FCRDP46K4SW3Z7ULAUOBAYT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VY7FCRDP46K4SW3Z7ULAUOBAYT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VY7FCRDP46K4SW3Z7ULAUOBAYT/action/storage_attestation","attest_author":"https://pith.science/pith/VY7FCRDP46K4SW3Z7ULAUOBAYT/action/author_attestation","sign_citation":"https://pith.science/pith/VY7FCRDP46K4SW3Z7ULAUOBAYT/action/citation_signature","submit_replication":"https://pith.science/pith/VY7FCRDP46K4SW3Z7ULAUOBAYT/action/replication_record"}},"created_at":"2026-05-18T00:22:13.342238+00:00","updated_at":"2026-05-18T00:22:13.342238+00:00"}