{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:F7226DSQPZKJHDMSSBEVRPCQUF","short_pith_number":"pith:F7226DSQ","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"},"canonical_sha256":"2ff5af0e507e54938d92904958bc50a162a03fe04abf57e914d65e2bdfd6fe89","source":{"kind":"arxiv","id":"1910.03358","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.03358","created_at":"2026-07-05T00:10:20Z"},{"alias_kind":"arxiv_version","alias_value":"1910.03358v1","created_at":"2026-07-05T00:10:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.03358","created_at":"2026-07-05T00:10:20Z"},{"alias_kind":"pith_short_12","alias_value":"F7226DSQPZKJ","created_at":"2026-07-05T00:10:20Z"},{"alias_kind":"pith_short_16","alias_value":"F7226DSQPZKJHDMS","created_at":"2026-07-05T00:10:20Z"},{"alias_kind":"pith_short_8","alias_value":"F7226DSQ","created_at":"2026-07-05T00:10:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:F7226DSQPZKJHDMSSBEVRPCQUF","target":"record","payload":{"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"},"canonical_sha256":"2ff5af0e507e54938d92904958bc50a162a03fe04abf57e914d65e2bdfd6fe89","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"},"source_kind":"arxiv","source_id":"1910.03358","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:10:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MfhX3wcjJSTFJjBaNBMLUIbkYVsLTFKESn6ZkIg08o90sU3PSMg2sLDRQQqEAHMg2S8QPmyNPmyNY1TIt+YKCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:55:11.403125Z"},"content_sha256":"f961e02120ad5708a4b1295c1d928559945c140c2e77fee16070f1c5d6f722c6","schema_version":"1.0","event_id":"sha256:f961e02120ad5708a4b1295c1d928559945c140c2e77fee16070f1c5d6f722c6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:F7226DSQPZKJHDMSSBEVRPCQUF","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:10:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zYZ7kA6A09cuXVRxTJrWyYfJe3cnjRItXWQSj64zvbkJGKQxMBCCHx9c6IHjya6sp7No7fU00ica8kB492ZTDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:55:11.403778Z"},"content_sha256":"80d214eb2555280a6e71082ffc282c57375fd366318a6fea17b02bd10bf18ed0","schema_version":"1.0","event_id":"sha256:80d214eb2555280a6e71082ffc282c57375fd366318a6fea17b02bd10bf18ed0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F7226DSQPZKJHDMSSBEVRPCQUF/bundle.json","state_url":"https://pith.science/pith/F7226DSQPZKJHDMSSBEVRPCQUF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F7226DSQPZKJHDMSSBEVRPCQUF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-09T06:55:11Z","links":{"resolver":"https://pith.science/pith/F7226DSQPZKJHDMSSBEVRPCQUF","bundle":"https://pith.science/pith/F7226DSQPZKJHDMSSBEVRPCQUF/bundle.json","state":"https://pith.science/pith/F7226DSQPZKJHDMSSBEVRPCQUF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F7226DSQPZKJHDMSSBEVRPCQUF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:F7226DSQPZKJHDMSSBEVRPCQUF","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":"db126f0c073e48bac6f3ecd5687dcd826564bc673873539b0f0d3b3f572a0a16","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-08T12:19:50Z","title_canon_sha256":"5c70910123362894860f3bf4eac531194bb6fb314d5db11a2786117e3cb12be7"},"schema_version":"1.0","source":{"id":"1910.03358","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.03358","created_at":"2026-07-05T00:10:20Z"},{"alias_kind":"arxiv_version","alias_value":"1910.03358v1","created_at":"2026-07-05T00:10:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.03358","created_at":"2026-07-05T00:10:20Z"},{"alias_kind":"pith_short_12","alias_value":"F7226DSQPZKJ","created_at":"2026-07-05T00:10:20Z"},{"alias_kind":"pith_short_16","alias_value":"F7226DSQPZKJHDMS","created_at":"2026-07-05T00:10:20Z"},{"alias_kind":"pith_short_8","alias_value":"F7226DSQ","created_at":"2026-07-05T00:10:20Z"}],"graph_snapshots":[{"event_id":"sha256:80d214eb2555280a6e71082ffc282c57375fd366318a6fea17b02bd10bf18ed0","target":"graph","created_at":"2026-07-05T00:10:20Z","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/1910.03358/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"David Hoeller, Farbod Farshidian, Marco Hutter","cross_cats":["cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-08T12:19:50Z","title":"Deep Value Model Predictive Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.03358","kind":"arxiv","version":1},"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:f961e02120ad5708a4b1295c1d928559945c140c2e77fee16070f1c5d6f722c6","target":"record","created_at":"2026-07-05T00:10:20Z","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":"db126f0c073e48bac6f3ecd5687dcd826564bc673873539b0f0d3b3f572a0a16","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-08T12:19:50Z","title_canon_sha256":"5c70910123362894860f3bf4eac531194bb6fb314d5db11a2786117e3cb12be7"},"schema_version":"1.0","source":{"id":"1910.03358","kind":"arxiv","version":1}},"canonical_sha256":"2ff5af0e507e54938d92904958bc50a162a03fe04abf57e914d65e2bdfd6fe89","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ff5af0e507e54938d92904958bc50a162a03fe04abf57e914d65e2bdfd6fe89","first_computed_at":"2026-07-05T00:10:20.413840Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:10:20.413840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KzTaFCmIw/qUXGl5jimgBsKjHQwbf0l7ba+ba4GwxIpDO5sitFaG+345leWhztJJqnRq6gCFb+Bn4ZBrUnD/Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:10:20.414272Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.03358","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f961e02120ad5708a4b1295c1d928559945c140c2e77fee16070f1c5d6f722c6","sha256:80d214eb2555280a6e71082ffc282c57375fd366318a6fea17b02bd10bf18ed0"],"state_sha256":"55cbb4c3bc4f01b4945dfa851b4414153bd49f18ca589f19ab5bf698d53a9c84"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EvfvcbLWnAQHF1bVBtdFtyojwU/5hq+YD/EUE76QHSZUqqA/q2I0w9Ls2U5Dp/bUX9n8Rro3zS9ZrRYqRe2uDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T06:55:11.407220Z","bundle_sha256":"5a2d3ad0585ff5085e47168bfa1fe6b3b5bfb9c9219ae2d893c1e87e5ad4968b"}}