{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TMEZLTRLKVHPS6MMI3CMQLZUTV","short_pith_number":"pith:TMEZLTRL","schema_version":"1.0","canonical_sha256":"9b0995ce2b554ef9798c46c4c82f349d657dfa97e6739b87b7dcf1b8e4f07397","source":{"kind":"arxiv","id":"2209.08169","version":2},"attestation_state":"computed","paper":{"title":"Value Summation: A Novel Scoring Function for MPC-based Model-based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Amirhossein Noohian, Luc McCutcheon, Mehran Raisi, Saber Fallah","submitted_at":"2022-09-16T20:52:39Z","abstract_excerpt":"This paper proposes a novel scoring function for the planning module of MPC-based reinforcement learning methods to address the inherent bias of using the reward function to score trajectories. The proposed method enhances the learning efficiency of existing MPC-based MBRL methods using the discounted sum of values. The method utilizes optimal trajectories to guide policy learning and updates its state-action value function based on real-world and augmented onboard data. The learning efficiency of the proposed method is evaluated in selected MuJoCo Gym environments as well as in learning locom"},"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":"2209.08169","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-16T20:52:39Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"1800feeca7331b2075e3e91966e1b047bd1142748402ce1a0cca7b4c532a023a","abstract_canon_sha256":"ae24398bb385d8f26f7bca83474e448c8b0b5b3b3adc8403e6fa33bcc1e348b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:32:34.267718Z","signature_b64":"XibgeJdlAHfQdhYeDqC2GsIXxtH13awiaBXR0dpaWomXJmhZEGzH6ymDY7ciXYk5dHm0prXcQUXjXzWiXof+CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b0995ce2b554ef9798c46c4c82f349d657dfa97e6739b87b7dcf1b8e4f07397","last_reissued_at":"2026-07-05T06:32:34.267291Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:32:34.267291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Value Summation: A Novel Scoring Function for MPC-based Model-based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Amirhossein Noohian, Luc McCutcheon, Mehran Raisi, Saber Fallah","submitted_at":"2022-09-16T20:52:39Z","abstract_excerpt":"This paper proposes a novel scoring function for the planning module of MPC-based reinforcement learning methods to address the inherent bias of using the reward function to score trajectories. The proposed method enhances the learning efficiency of existing MPC-based MBRL methods using the discounted sum of values. The method utilizes optimal trajectories to guide policy learning and updates its state-action value function based on real-world and augmented onboard data. The learning efficiency of the proposed method is evaluated in selected MuJoCo Gym environments as well as in learning locom"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.08169","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/2209.08169/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":"2209.08169","created_at":"2026-07-05T06:32:34.267369+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.08169v2","created_at":"2026-07-05T06:32:34.267369+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.08169","created_at":"2026-07-05T06:32:34.267369+00:00"},{"alias_kind":"pith_short_12","alias_value":"TMEZLTRLKVHP","created_at":"2026-07-05T06:32:34.267369+00:00"},{"alias_kind":"pith_short_16","alias_value":"TMEZLTRLKVHPS6MM","created_at":"2026-07-05T06:32:34.267369+00:00"},{"alias_kind":"pith_short_8","alias_value":"TMEZLTRL","created_at":"2026-07-05T06:32:34.267369+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/TMEZLTRLKVHPS6MMI3CMQLZUTV","json":"https://pith.science/pith/TMEZLTRLKVHPS6MMI3CMQLZUTV.json","graph_json":"https://pith.science/api/pith-number/TMEZLTRLKVHPS6MMI3CMQLZUTV/graph.json","events_json":"https://pith.science/api/pith-number/TMEZLTRLKVHPS6MMI3CMQLZUTV/events.json","paper":"https://pith.science/paper/TMEZLTRL"},"agent_actions":{"view_html":"https://pith.science/pith/TMEZLTRLKVHPS6MMI3CMQLZUTV","download_json":"https://pith.science/pith/TMEZLTRLKVHPS6MMI3CMQLZUTV.json","view_paper":"https://pith.science/paper/TMEZLTRL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.08169&json=true","fetch_graph":"https://pith.science/api/pith-number/TMEZLTRLKVHPS6MMI3CMQLZUTV/graph.json","fetch_events":"https://pith.science/api/pith-number/TMEZLTRLKVHPS6MMI3CMQLZUTV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TMEZLTRLKVHPS6MMI3CMQLZUTV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TMEZLTRLKVHPS6MMI3CMQLZUTV/action/storage_attestation","attest_author":"https://pith.science/pith/TMEZLTRLKVHPS6MMI3CMQLZUTV/action/author_attestation","sign_citation":"https://pith.science/pith/TMEZLTRLKVHPS6MMI3CMQLZUTV/action/citation_signature","submit_replication":"https://pith.science/pith/TMEZLTRLKVHPS6MMI3CMQLZUTV/action/replication_record"}},"created_at":"2026-07-05T06:32:34.267369+00:00","updated_at":"2026-07-05T06:32:34.267369+00:00"}