{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4PNL5WFNJR3JHXC5R2OFWOBEXW","short_pith_number":"pith:4PNL5WFN","canonical_record":{"source":{"id":"2406.00592","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2024-06-02T02:01:03Z","cross_cats_sorted":["cs.AI","cs.SY","math.OC"],"title_canon_sha256":"46731b2392ceadc2ba6087996af6eae09ef0e1d9ea9f500b27cd1e1c9ea3696b","abstract_canon_sha256":"896bb1c13f9a3dd7fb88363e0feebd6a77bd38912b6767d6a31533166db3c910"},"schema_version":"1.0"},"canonical_sha256":"e3dabed8ad4c7693dc5d8e9c5b3824bd86e00dd4242b1b8205225d8d9a1155dd","source":{"kind":"arxiv","id":"2406.00592","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.00592","created_at":"2026-07-05T08:38:10Z"},{"alias_kind":"arxiv_version","alias_value":"2406.00592v3","created_at":"2026-07-05T08:38:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00592","created_at":"2026-07-05T08:38:10Z"},{"alias_kind":"pith_short_12","alias_value":"4PNL5WFNJR3J","created_at":"2026-07-05T08:38:10Z"},{"alias_kind":"pith_short_16","alias_value":"4PNL5WFNJR3JHXC5","created_at":"2026-07-05T08:38:10Z"},{"alias_kind":"pith_short_8","alias_value":"4PNL5WFN","created_at":"2026-07-05T08:38:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4PNL5WFNJR3JHXC5R2OFWOBEXW","target":"record","payload":{"canonical_record":{"source":{"id":"2406.00592","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2024-06-02T02:01:03Z","cross_cats_sorted":["cs.AI","cs.SY","math.OC"],"title_canon_sha256":"46731b2392ceadc2ba6087996af6eae09ef0e1d9ea9f500b27cd1e1c9ea3696b","abstract_canon_sha256":"896bb1c13f9a3dd7fb88363e0feebd6a77bd38912b6767d6a31533166db3c910"},"schema_version":"1.0"},"canonical_sha256":"e3dabed8ad4c7693dc5d8e9c5b3824bd86e00dd4242b1b8205225d8d9a1155dd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:10.171169Z","signature_b64":"3uEi040JUecmUT/3Ay27em6d2D2LnM/Zoj6Y2OJIng7Vcx/ihnuH85/VCq4UUJsZQyTS6w1Du4Lpt/AFkDITCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3dabed8ad4c7693dc5d8e9c5b3824bd86e00dd4242b1b8205225d8d9a1155dd","last_reissued_at":"2026-07-05T08:38:10.170683Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:10.170683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.00592","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:38:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"msnlUieWXaPSS/hKF6LOAFadUvUgYR2Tn2JZ//uRP4hZqzJQ6cekI6nQKtCcHL8BVus5eVRkBn4u0vTtQKH5Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:58:33.173268Z"},"content_sha256":"36eb6873bd24ffca72f08ae21ab07fd5f05dd6c39e434bcf40bfb2560733920d","schema_version":"1.0","event_id":"sha256:36eb6873bd24ffca72f08ae21ab07fd5f05dd6c39e434bcf40bfb2560733920d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4PNL5WFNJR3JHXC5R2OFWOBEXW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Model Predictive Control and Reinforcement Learning: A Unified Framework Based on Dynamic Programming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","math.OC"],"primary_cat":"eess.SY","authors_text":"Dimitri P. Bertsekas","submitted_at":"2024-06-02T02:01:03Z","abstract_excerpt":"In this paper we describe a new conceptual framework that connects approximate Dynamic Programming (DP), Model Predictive Control (MPC), and Reinforcement Learning (RL). This framework centers around two algorithms, which are designed largely independently of each other and operate in synergy through the powerful mechanism of Newton's method. We call them the off-line training and the on-line play algorithms. The names are borrowed from some of the major successes of RL involving games; primary examples are the recent (2017) AlphaZero program (which plays chess, [SHS17], [SSS17]), and the simi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00592","kind":"arxiv","version":3},"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/2406.00592/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":"2026-07-05T08:38:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NHbYkjPOYgHLaBrPpmWFsimTtUtTRswldkJRJ93LAWBw2t+RP3YeYLcR0BiRLY91YjmISUOlsGfh7qR7RyVjDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:58:33.173768Z"},"content_sha256":"63737a0b5d2966ee9a9ffed74be0fc976c8fb9f2cdbe9479719e1471844b1c5f","schema_version":"1.0","event_id":"sha256:63737a0b5d2966ee9a9ffed74be0fc976c8fb9f2cdbe9479719e1471844b1c5f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4PNL5WFNJR3JHXC5R2OFWOBEXW/bundle.json","state_url":"https://pith.science/pith/4PNL5WFNJR3JHXC5R2OFWOBEXW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4PNL5WFNJR3JHXC5R2OFWOBEXW/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":"2026-08-08T06:58:33Z","links":{"resolver":"https://pith.science/pith/4PNL5WFNJR3JHXC5R2OFWOBEXW","bundle":"https://pith.science/pith/4PNL5WFNJR3JHXC5R2OFWOBEXW/bundle.json","state":"https://pith.science/pith/4PNL5WFNJR3JHXC5R2OFWOBEXW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4PNL5WFNJR3JHXC5R2OFWOBEXW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4PNL5WFNJR3JHXC5R2OFWOBEXW","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":"896bb1c13f9a3dd7fb88363e0feebd6a77bd38912b6767d6a31533166db3c910","cross_cats_sorted":["cs.AI","cs.SY","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2024-06-02T02:01:03Z","title_canon_sha256":"46731b2392ceadc2ba6087996af6eae09ef0e1d9ea9f500b27cd1e1c9ea3696b"},"schema_version":"1.0","source":{"id":"2406.00592","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.00592","created_at":"2026-07-05T08:38:10Z"},{"alias_kind":"arxiv_version","alias_value":"2406.00592v3","created_at":"2026-07-05T08:38:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00592","created_at":"2026-07-05T08:38:10Z"},{"alias_kind":"pith_short_12","alias_value":"4PNL5WFNJR3J","created_at":"2026-07-05T08:38:10Z"},{"alias_kind":"pith_short_16","alias_value":"4PNL5WFNJR3JHXC5","created_at":"2026-07-05T08:38:10Z"},{"alias_kind":"pith_short_8","alias_value":"4PNL5WFN","created_at":"2026-07-05T08:38:10Z"}],"graph_snapshots":[{"event_id":"sha256:63737a0b5d2966ee9a9ffed74be0fc976c8fb9f2cdbe9479719e1471844b1c5f","target":"graph","created_at":"2026-07-05T08:38:10Z","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/2406.00592/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper we describe a new conceptual framework that connects approximate Dynamic Programming (DP), Model Predictive Control (MPC), and Reinforcement Learning (RL). This framework centers around two algorithms, which are designed largely independently of each other and operate in synergy through the powerful mechanism of Newton's method. We call them the off-line training and the on-line play algorithms. The names are borrowed from some of the major successes of RL involving games; primary examples are the recent (2017) AlphaZero program (which plays chess, [SHS17], [SSS17]), and the simi","authors_text":"Dimitri P. Bertsekas","cross_cats":["cs.AI","cs.SY","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2024-06-02T02:01:03Z","title":"Model Predictive Control and Reinforcement Learning: A Unified Framework Based on Dynamic Programming"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00592","kind":"arxiv","version":3},"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":"sha256:36eb6873bd24ffca72f08ae21ab07fd5f05dd6c39e434bcf40bfb2560733920d","target":"record","created_at":"2026-07-05T08:38:10Z","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":"896bb1c13f9a3dd7fb88363e0feebd6a77bd38912b6767d6a31533166db3c910","cross_cats_sorted":["cs.AI","cs.SY","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2024-06-02T02:01:03Z","title_canon_sha256":"46731b2392ceadc2ba6087996af6eae09ef0e1d9ea9f500b27cd1e1c9ea3696b"},"schema_version":"1.0","source":{"id":"2406.00592","kind":"arxiv","version":3}},"canonical_sha256":"e3dabed8ad4c7693dc5d8e9c5b3824bd86e00dd4242b1b8205225d8d9a1155dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3dabed8ad4c7693dc5d8e9c5b3824bd86e00dd4242b1b8205225d8d9a1155dd","first_computed_at":"2026-07-05T08:38:10.170683Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:38:10.170683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3uEi040JUecmUT/3Ay27em6d2D2LnM/Zoj6Y2OJIng7Vcx/ihnuH85/VCq4UUJsZQyTS6w1Du4Lpt/AFkDITCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:38:10.171169Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.00592","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36eb6873bd24ffca72f08ae21ab07fd5f05dd6c39e434bcf40bfb2560733920d","sha256:63737a0b5d2966ee9a9ffed74be0fc976c8fb9f2cdbe9479719e1471844b1c5f"],"state_sha256":"fa90519df82af4d44bc8d313b60a667910fd7710510256d9555a7aa5acf9237e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l+68Hk2Al99lZYPmVnT1jTPkLxy4dfNCXU7KhdKZ+Gi1qWTkCGa9x2xLJATAQ4IP7lEjWa9YtxZ9SU23+ygqBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T06:58:33.178927Z","bundle_sha256":"b8624b2d894303c98ddc8e8dbede9463251362dc26aa945407503eea7ef3d303"}}