{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MQXJDGDINNOLCN4FKC7M6T7YOW","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":"08e2b5647dd94fa027b12a709c04f020d517714cbb341ac605b942f40328bacb","cross_cats_sorted":["cs.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2021-06-16T08:39:51Z","title_canon_sha256":"0ab60357661a9046d8154bfd94570913c44afc5fdfd90bb02d729b2cdc7abc07"},"schema_version":"1.0","source":{"id":"2106.08634","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.08634","created_at":"2026-07-05T03:03:28Z"},{"alias_kind":"arxiv_version","alias_value":"2106.08634v2","created_at":"2026-07-05T03:03:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.08634","created_at":"2026-07-05T03:03:28Z"},{"alias_kind":"pith_short_12","alias_value":"MQXJDGDINNOL","created_at":"2026-07-05T03:03:28Z"},{"alias_kind":"pith_short_16","alias_value":"MQXJDGDINNOLCN4F","created_at":"2026-07-05T03:03:28Z"},{"alias_kind":"pith_short_8","alias_value":"MQXJDGDI","created_at":"2026-07-05T03:03:28Z"}],"graph_snapshots":[{"event_id":"sha256:7e4077ed3b40f6211c8aa995bde787dc24304ba7bb30490cba6eb6177cedf528","target":"graph","created_at":"2026-07-05T03:03:28Z","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/2106.08634/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Anastasios M. Lekkas, Arash B. Kordabad, Hossein N. Esfahani, Sebastien Gros, Wenqi Cai","cross_cats":["cs.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2021-06-16T08:39:51Z","title":"MPC-based Reinforcement Learning for a Simplified Freight Mission of Autonomous Surface Vehicles"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.08634","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:a82c9f2860dbeb4d94040ce280bcb4e50bbde9a3b460104eeaa3b0ab6f87bdd9","target":"record","created_at":"2026-07-05T03:03:28Z","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":"08e2b5647dd94fa027b12a709c04f020d517714cbb341ac605b942f40328bacb","cross_cats_sorted":["cs.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2021-06-16T08:39:51Z","title_canon_sha256":"0ab60357661a9046d8154bfd94570913c44afc5fdfd90bb02d729b2cdc7abc07"},"schema_version":"1.0","source":{"id":"2106.08634","kind":"arxiv","version":2}},"canonical_sha256":"642e9198686b5cb1378550becf4ff875b1f559cd022ee9d1487a1b2796c3a4cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"642e9198686b5cb1378550becf4ff875b1f559cd022ee9d1487a1b2796c3a4cd","first_computed_at":"2026-07-05T03:03:28.810606Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:03:28.810606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b6UK00I8hI8GB9TtXtLoYXT8xWSNw+DGMEISlex7U9hmegqdrQ6rmw2pNBGb0trlVxdetxwKXizz96zdVGMeDw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:03:28.811030Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.08634","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a82c9f2860dbeb4d94040ce280bcb4e50bbde9a3b460104eeaa3b0ab6f87bdd9","sha256:7e4077ed3b40f6211c8aa995bde787dc24304ba7bb30490cba6eb6177cedf528"],"state_sha256":"8561a74b400e9069f52f4505556c35916acc2aa76632d57d0889387fc375e44f"}