{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:QNAXC4ATTUQGWZP6DXROV7RJU5","short_pith_number":"pith:QNAXC4AT","canonical_record":{"source":{"id":"2012.05909","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-10T11:32:01Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"aff684b121e3e18850363360eafba43b9c60ddce5241ea9e9694d200f83167b2","abstract_canon_sha256":"44b6162ee28f76785e6b9974a46447df4a4e10f06387959de9962f73c76996f1"},"schema_version":"1.0"},"canonical_sha256":"83417170139d206b65fe1de2eafe29a77fb41e276f657e175f47d1011ee36406","source":{"kind":"arxiv","id":"2012.05909","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.05909","created_at":"2026-07-05T02:32:02Z"},{"alias_kind":"arxiv_version","alias_value":"2012.05909v2","created_at":"2026-07-05T02:32:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.05909","created_at":"2026-07-05T02:32:02Z"},{"alias_kind":"pith_short_12","alias_value":"QNAXC4ATTUQG","created_at":"2026-07-05T02:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"QNAXC4ATTUQGWZP6","created_at":"2026-07-05T02:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"QNAXC4AT","created_at":"2026-07-05T02:32:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:QNAXC4ATTUQGWZP6DXROV7RJU5","target":"record","payload":{"canonical_record":{"source":{"id":"2012.05909","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-10T11:32:01Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"aff684b121e3e18850363360eafba43b9c60ddce5241ea9e9694d200f83167b2","abstract_canon_sha256":"44b6162ee28f76785e6b9974a46447df4a4e10f06387959de9962f73c76996f1"},"schema_version":"1.0"},"canonical_sha256":"83417170139d206b65fe1de2eafe29a77fb41e276f657e175f47d1011ee36406","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:32:02.390399Z","signature_b64":"ekLZJj1IpBHL9jmIeda5+HkH70EiWLc3dF7NEg6Xzd60tYgmp4WhaSHLSBtcjZ3npulKz9ep70yYrhi4+G+BCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83417170139d206b65fe1de2eafe29a77fb41e276f657e175f47d1011ee36406","last_reissued_at":"2026-07-05T02:32:02.389870Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:32:02.389870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.05909","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:32:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fI132qy3+Hf0romk0u5v2qWJu4HLgM2SxOfHAUj6K02dYI6TGzyxib+OFk+s537fkHIPkqltk3Ad716e/rVNAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T15:42:47.442966Z"},"content_sha256":"23ee41d214262d9807c94855ad285670e53203bcef83a8d2e842503fb71a684e","schema_version":"1.0","event_id":"sha256:23ee41d214262d9807c94855ad285670e53203bcef83a8d2e842503fb71a684e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:QNAXC4ATTUQGWZP6DXROV7RJU5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Blending MPC & Value Function Approximation for Efficient Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Byron Boots, Mohak Bhardwaj, Sanjiban Choudhury","submitted_at":"2020-12-10T11:32:01Z","abstract_excerpt":"Model-Predictive Control (MPC) is a powerful tool for controlling complex, real-world systems that uses a model to make predictions about future behavior. For each state encountered, MPC solves an online optimization problem to choose a control action that will minimize future cost. This is a surprisingly effective strategy, but real-time performance requirements warrant the use of simple models. If the model is not sufficiently accurate, then the resulting controller can be biased, limiting performance. We present a framework for improving on MPC with model-free reinforcement learning (RL). T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.05909","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/2012.05909/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":"2026-07-05T02:32:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FFmwYpuueGYubkApxs3BS4jvnfXq04MGg8REdXy2Vbyeq+LoYLlVocU6ziArrbL4pxqkeehmntBtwt2kTzmyBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T15:42:47.443924Z"},"content_sha256":"fe7073c7f10a59c6107adedb81eb0ab434d5b6095764e3e01b13227e5e8dd3cd","schema_version":"1.0","event_id":"sha256:fe7073c7f10a59c6107adedb81eb0ab434d5b6095764e3e01b13227e5e8dd3cd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QNAXC4ATTUQGWZP6DXROV7RJU5/bundle.json","state_url":"https://pith.science/pith/QNAXC4ATTUQGWZP6DXROV7RJU5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QNAXC4ATTUQGWZP6DXROV7RJU5/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":"2026-08-18T15:42:47Z","links":{"resolver":"https://pith.science/pith/QNAXC4ATTUQGWZP6DXROV7RJU5","bundle":"https://pith.science/pith/QNAXC4ATTUQGWZP6DXROV7RJU5/bundle.json","state":"https://pith.science/pith/QNAXC4ATTUQGWZP6DXROV7RJU5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QNAXC4ATTUQGWZP6DXROV7RJU5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:QNAXC4ATTUQGWZP6DXROV7RJU5","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":"44b6162ee28f76785e6b9974a46447df4a4e10f06387959de9962f73c76996f1","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-10T11:32:01Z","title_canon_sha256":"aff684b121e3e18850363360eafba43b9c60ddce5241ea9e9694d200f83167b2"},"schema_version":"1.0","source":{"id":"2012.05909","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.05909","created_at":"2026-07-05T02:32:02Z"},{"alias_kind":"arxiv_version","alias_value":"2012.05909v2","created_at":"2026-07-05T02:32:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.05909","created_at":"2026-07-05T02:32:02Z"},{"alias_kind":"pith_short_12","alias_value":"QNAXC4ATTUQG","created_at":"2026-07-05T02:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"QNAXC4ATTUQGWZP6","created_at":"2026-07-05T02:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"QNAXC4AT","created_at":"2026-07-05T02:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:fe7073c7f10a59c6107adedb81eb0ab434d5b6095764e3e01b13227e5e8dd3cd","target":"graph","created_at":"2026-07-05T02:32:02Z","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/2012.05909/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-Predictive Control (MPC) is a powerful tool for controlling complex, real-world systems that uses a model to make predictions about future behavior. For each state encountered, MPC solves an online optimization problem to choose a control action that will minimize future cost. This is a surprisingly effective strategy, but real-time performance requirements warrant the use of simple models. If the model is not sufficiently accurate, then the resulting controller can be biased, limiting performance. We present a framework for improving on MPC with model-free reinforcement learning (RL). T","authors_text":"Byron Boots, Mohak Bhardwaj, Sanjiban Choudhury","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-10T11:32:01Z","title":"Blending MPC & Value Function Approximation for Efficient Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.05909","kind":"arxiv","version":2},"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":"sha256:23ee41d214262d9807c94855ad285670e53203bcef83a8d2e842503fb71a684e","target":"record","created_at":"2026-07-05T02:32:02Z","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":"44b6162ee28f76785e6b9974a46447df4a4e10f06387959de9962f73c76996f1","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-10T11:32:01Z","title_canon_sha256":"aff684b121e3e18850363360eafba43b9c60ddce5241ea9e9694d200f83167b2"},"schema_version":"1.0","source":{"id":"2012.05909","kind":"arxiv","version":2}},"canonical_sha256":"83417170139d206b65fe1de2eafe29a77fb41e276f657e175f47d1011ee36406","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83417170139d206b65fe1de2eafe29a77fb41e276f657e175f47d1011ee36406","first_computed_at":"2026-07-05T02:32:02.389870Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:32:02.389870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ekLZJj1IpBHL9jmIeda5+HkH70EiWLc3dF7NEg6Xzd60tYgmp4WhaSHLSBtcjZ3npulKz9ep70yYrhi4+G+BCg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:32:02.390399Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.05909","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23ee41d214262d9807c94855ad285670e53203bcef83a8d2e842503fb71a684e","sha256:fe7073c7f10a59c6107adedb81eb0ab434d5b6095764e3e01b13227e5e8dd3cd"],"state_sha256":"deccb0691d3e5dd1e6c2ffd154f0a164af2706bd36e91b1f606a13bf5eca2d60"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dApVbJnv8YLw0euH+ajfejK7F8uHSYoAdmYzlvpKbp3FCb7pdJA93ZJIgW4FHSCWgNrQY+9bqg6FpBF3ZBoCBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T15:42:47.450245Z","bundle_sha256":"5a6fdc595b6e00ce1167c7aef77a73cb98187fe14582a3ff4a6490e243b35357"}}