{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MQXJDGDINNOLCN4FKC7M6T7YOW","short_pith_number":"pith:MQXJDGDI","schema_version":"1.0","canonical_sha256":"642e9198686b5cb1378550becf4ff875b1f559cd022ee9d1487a1b2796c3a4cd","source":{"kind":"arxiv","id":"2106.08634","version":2},"attestation_state":"computed","paper":{"title":"MPC-based Reinforcement Learning for a Simplified Freight Mission of Autonomous Surface Vehicles","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Anastasios M. Lekkas, Arash B. Kordabad, Hossein N. Esfahani, Sebastien Gros, Wenqi Cai","submitted_at":"2021-06-16T08:39:51Z","abstract_excerpt":"In this work, we propose a Model Predictive Control (MPC)-based Reinforcement Learning (RL) method for Autonomous Surface Vehicles (ASVs). The objective is to find an optimal policy that minimizes the closed-loop performance of a simplified freight mission, including collision-free path following, autonomous docking, and a skillful transition between them. We use a parametrized MPC-scheme to approximate the optimal policy, which considers path-following/docking costs and states (position, velocity)/inputs (thruster force, angle) constraints. The Least Squares Temporal Difference (LSTD)-based D"},"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":"2106.08634","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2021-06-16T08:39:51Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"0ab60357661a9046d8154bfd94570913c44afc5fdfd90bb02d729b2cdc7abc07","abstract_canon_sha256":"08e2b5647dd94fa027b12a709c04f020d517714cbb341ac605b942f40328bacb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:03:28.811030Z","signature_b64":"b6UK00I8hI8GB9TtXtLoYXT8xWSNw+DGMEISlex7U9hmegqdrQ6rmw2pNBGb0trlVxdetxwKXizz96zdVGMeDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"642e9198686b5cb1378550becf4ff875b1f559cd022ee9d1487a1b2796c3a4cd","last_reissued_at":"2026-07-05T03:03:28.810606Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:03:28.810606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MPC-based Reinforcement Learning for a Simplified Freight Mission of Autonomous Surface Vehicles","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Anastasios M. Lekkas, Arash B. Kordabad, Hossein N. Esfahani, Sebastien Gros, Wenqi Cai","submitted_at":"2021-06-16T08:39:51Z","abstract_excerpt":"In this work, we propose a Model Predictive Control (MPC)-based Reinforcement Learning (RL) method for Autonomous Surface Vehicles (ASVs). The objective is to find an optimal policy that minimizes the closed-loop performance of a simplified freight mission, including collision-free path following, autonomous docking, and a skillful transition between them. We use a parametrized MPC-scheme to approximate the optimal policy, which considers path-following/docking costs and states (position, velocity)/inputs (thruster force, angle) constraints. The Least Squares Temporal Difference (LSTD)-based D"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.08634","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/2106.08634/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":"2106.08634","created_at":"2026-07-05T03:03:28.810663+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.08634v2","created_at":"2026-07-05T03:03:28.810663+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.08634","created_at":"2026-07-05T03:03:28.810663+00:00"},{"alias_kind":"pith_short_12","alias_value":"MQXJDGDINNOL","created_at":"2026-07-05T03:03:28.810663+00:00"},{"alias_kind":"pith_short_16","alias_value":"MQXJDGDINNOLCN4F","created_at":"2026-07-05T03:03:28.810663+00:00"},{"alias_kind":"pith_short_8","alias_value":"MQXJDGDI","created_at":"2026-07-05T03:03:28.810663+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.13491","citing_title":"Model-free Reinforcement Learning for Model-based Control: Towards Safe, Interpretable and Sample-efficient Agents","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MQXJDGDINNOLCN4FKC7M6T7YOW","json":"https://pith.science/pith/MQXJDGDINNOLCN4FKC7M6T7YOW.json","graph_json":"https://pith.science/api/pith-number/MQXJDGDINNOLCN4FKC7M6T7YOW/graph.json","events_json":"https://pith.science/api/pith-number/MQXJDGDINNOLCN4FKC7M6T7YOW/events.json","paper":"https://pith.science/paper/MQXJDGDI"},"agent_actions":{"view_html":"https://pith.science/pith/MQXJDGDINNOLCN4FKC7M6T7YOW","download_json":"https://pith.science/pith/MQXJDGDINNOLCN4FKC7M6T7YOW.json","view_paper":"https://pith.science/paper/MQXJDGDI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.08634&json=true","fetch_graph":"https://pith.science/api/pith-number/MQXJDGDINNOLCN4FKC7M6T7YOW/graph.json","fetch_events":"https://pith.science/api/pith-number/MQXJDGDINNOLCN4FKC7M6T7YOW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MQXJDGDINNOLCN4FKC7M6T7YOW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MQXJDGDINNOLCN4FKC7M6T7YOW/action/storage_attestation","attest_author":"https://pith.science/pith/MQXJDGDINNOLCN4FKC7M6T7YOW/action/author_attestation","sign_citation":"https://pith.science/pith/MQXJDGDINNOLCN4FKC7M6T7YOW/action/citation_signature","submit_replication":"https://pith.science/pith/MQXJDGDINNOLCN4FKC7M6T7YOW/action/replication_record"}},"created_at":"2026-07-05T03:03:28.810663+00:00","updated_at":"2026-07-05T03:03:28.810663+00:00"}