{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:F7226DSQPZKJHDMSSBEVRPCQUF","short_pith_number":"pith:F7226DSQ","schema_version":"1.0","canonical_sha256":"2ff5af0e507e54938d92904958bc50a162a03fe04abf57e914d65e2bdfd6fe89","source":{"kind":"arxiv","id":"1910.03358","version":1},"attestation_state":"computed","paper":{"title":"Deep Value Model Predictive Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Hoeller, Farbod Farshidian, Marco Hutter","submitted_at":"2019-10-08T12:19:50Z","abstract_excerpt":"In this paper, we introduce an actor-critic algorithm called Deep Value Model Predictive Control (DMPC), which combines model-based trajectory optimization with value function estimation. The DMPC actor is a Model Predictive Control (MPC) optimizer with an objective function defined in terms of a value function estimated by the critic. We show that our MPC actor is an importance sampler, which minimizes an upper bound of the cross-entropy to the state distribution of the optimal sampling policy. In our experiments with a Ballbot system, we show that our algorithm can work with sparse and binar"},"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":"1910.03358","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-08T12:19:50Z","cross_cats_sorted":["cs.RO","stat.ML"],"title_canon_sha256":"5c70910123362894860f3bf4eac531194bb6fb314d5db11a2786117e3cb12be7","abstract_canon_sha256":"db126f0c073e48bac6f3ecd5687dcd826564bc673873539b0f0d3b3f572a0a16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:10:20.414272Z","signature_b64":"KzTaFCmIw/qUXGl5jimgBsKjHQwbf0l7ba+ba4GwxIpDO5sitFaG+345leWhztJJqnRq6gCFb+Bn4ZBrUnD/Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ff5af0e507e54938d92904958bc50a162a03fe04abf57e914d65e2bdfd6fe89","last_reissued_at":"2026-07-05T00:10:20.413840Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:10:20.413840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Value Model Predictive Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Hoeller, Farbod Farshidian, Marco Hutter","submitted_at":"2019-10-08T12:19:50Z","abstract_excerpt":"In this paper, we introduce an actor-critic algorithm called Deep Value Model Predictive Control (DMPC), which combines model-based trajectory optimization with value function estimation. The DMPC actor is a Model Predictive Control (MPC) optimizer with an objective function defined in terms of a value function estimated by the critic. We show that our MPC actor is an importance sampler, which minimizes an upper bound of the cross-entropy to the state distribution of the optimal sampling policy. In our experiments with a Ballbot system, we show that our algorithm can work with sparse and binar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.03358","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1910.03358/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":"1910.03358","created_at":"2026-07-05T00:10:20.413897+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.03358v1","created_at":"2026-07-05T00:10:20.413897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.03358","created_at":"2026-07-05T00:10:20.413897+00:00"},{"alias_kind":"pith_short_12","alias_value":"F7226DSQPZKJ","created_at":"2026-07-05T00:10:20.413897+00:00"},{"alias_kind":"pith_short_16","alias_value":"F7226DSQPZKJHDMS","created_at":"2026-07-05T00:10:20.413897+00:00"},{"alias_kind":"pith_short_8","alias_value":"F7226DSQ","created_at":"2026-07-05T00:10:20.413897+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F7226DSQPZKJHDMSSBEVRPCQUF","json":"https://pith.science/pith/F7226DSQPZKJHDMSSBEVRPCQUF.json","graph_json":"https://pith.science/api/pith-number/F7226DSQPZKJHDMSSBEVRPCQUF/graph.json","events_json":"https://pith.science/api/pith-number/F7226DSQPZKJHDMSSBEVRPCQUF/events.json","paper":"https://pith.science/paper/F7226DSQ"},"agent_actions":{"view_html":"https://pith.science/pith/F7226DSQPZKJHDMSSBEVRPCQUF","download_json":"https://pith.science/pith/F7226DSQPZKJHDMSSBEVRPCQUF.json","view_paper":"https://pith.science/paper/F7226DSQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.03358&json=true","fetch_graph":"https://pith.science/api/pith-number/F7226DSQPZKJHDMSSBEVRPCQUF/graph.json","fetch_events":"https://pith.science/api/pith-number/F7226DSQPZKJHDMSSBEVRPCQUF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F7226DSQPZKJHDMSSBEVRPCQUF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F7226DSQPZKJHDMSSBEVRPCQUF/action/storage_attestation","attest_author":"https://pith.science/pith/F7226DSQPZKJHDMSSBEVRPCQUF/action/author_attestation","sign_citation":"https://pith.science/pith/F7226DSQPZKJHDMSSBEVRPCQUF/action/citation_signature","submit_replication":"https://pith.science/pith/F7226DSQPZKJHDMSSBEVRPCQUF/action/replication_record"}},"created_at":"2026-07-05T00:10:20.413897+00:00","updated_at":"2026-07-05T00:10:20.413897+00:00"}