{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MNMYYRL73V62RVFTUZ5OGANOFU","short_pith_number":"pith:MNMYYRL7","schema_version":"1.0","canonical_sha256":"63598c457fdd7da8d4b3a67ae301ae2d2e08b1e552472eb1f90dd27c74b9d267","source":{"kind":"arxiv","id":"2104.09785","version":2},"attestation_state":"computed","paper":{"title":"Model-predictive control and reinforcement learning in multi-energy system case studies","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SY","math.OC"],"primary_cat":"eess.SY","authors_text":"Alberte Bouso Garc\\'ia, Ann Now\\'e, Geert Deconinck, Glenn Ceusters, Lieve Helsen, Luis Ramirez Camargo, Maarten Messagie, Rom\\'an Cant\\'u Rodr\\'iguez, R\\\"udiger Franke","submitted_at":"2021-04-20T06:51:50Z","abstract_excerpt":"Model-predictive-control (MPC) offers an optimal control technique to establish and ensure that the total operation cost of multi-energy systems remains at a minimum while fulfilling all system constraints. However, this method presumes an adequate model of the underlying system dynamics, which is prone to modelling errors and is not necessarily adaptive. This has an associated initial and ongoing project-specific engineering cost. In this paper, we present an on- and off-policy multi-objective reinforcement learning (RL) approach, that does not assume a model a priori, benchmarking this again"},"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":"2104.09785","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.SY","submitted_at":"2021-04-20T06:51:50Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SY","math.OC"],"title_canon_sha256":"1c354ef73cab17e60aad80d14badbb29a2931801866981623acf960dcd0ca174","abstract_canon_sha256":"a8182239a31f9edf714a9dc3b9289e3eebfbe5e19a2b280de15e079a1a15807a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:12:48.543347Z","signature_b64":"xI62Cobb4GbramUDyhuyVFihs0jnLqDaxFxn39iUF3lkKDy4Ht0lenXjKUiXerYwP/Jvj2X+Q9sbIqPx9+tLCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63598c457fdd7da8d4b3a67ae301ae2d2e08b1e552472eb1f90dd27c74b9d267","last_reissued_at":"2026-07-05T03:12:48.542722Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:12:48.542722Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-predictive control and reinforcement learning in multi-energy system case studies","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SY","math.OC"],"primary_cat":"eess.SY","authors_text":"Alberte Bouso Garc\\'ia, Ann Now\\'e, Geert Deconinck, Glenn Ceusters, Lieve Helsen, Luis Ramirez Camargo, Maarten Messagie, Rom\\'an Cant\\'u Rodr\\'iguez, R\\\"udiger Franke","submitted_at":"2021-04-20T06:51:50Z","abstract_excerpt":"Model-predictive-control (MPC) offers an optimal control technique to establish and ensure that the total operation cost of multi-energy systems remains at a minimum while fulfilling all system constraints. However, this method presumes an adequate model of the underlying system dynamics, which is prone to modelling errors and is not necessarily adaptive. This has an associated initial and ongoing project-specific engineering cost. In this paper, we present an on- and off-policy multi-objective reinforcement learning (RL) approach, that does not assume a model a priori, benchmarking this again"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.09785","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/2104.09785/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":"2104.09785","created_at":"2026-07-05T03:12:48.542822+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.09785v2","created_at":"2026-07-05T03:12:48.542822+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.09785","created_at":"2026-07-05T03:12:48.542822+00:00"},{"alias_kind":"pith_short_12","alias_value":"MNMYYRL73V62","created_at":"2026-07-05T03:12:48.542822+00:00"},{"alias_kind":"pith_short_16","alias_value":"MNMYYRL73V62RVFT","created_at":"2026-07-05T03:12:48.542822+00:00"},{"alias_kind":"pith_short_8","alias_value":"MNMYYRL7","created_at":"2026-07-05T03:12:48.542822+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.20946","citing_title":"Generalising Battery Control in Net-Zero Buildings via Personalised Federated RL","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MNMYYRL73V62RVFTUZ5OGANOFU","json":"https://pith.science/pith/MNMYYRL73V62RVFTUZ5OGANOFU.json","graph_json":"https://pith.science/api/pith-number/MNMYYRL73V62RVFTUZ5OGANOFU/graph.json","events_json":"https://pith.science/api/pith-number/MNMYYRL73V62RVFTUZ5OGANOFU/events.json","paper":"https://pith.science/paper/MNMYYRL7"},"agent_actions":{"view_html":"https://pith.science/pith/MNMYYRL73V62RVFTUZ5OGANOFU","download_json":"https://pith.science/pith/MNMYYRL73V62RVFTUZ5OGANOFU.json","view_paper":"https://pith.science/paper/MNMYYRL7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.09785&json=true","fetch_graph":"https://pith.science/api/pith-number/MNMYYRL73V62RVFTUZ5OGANOFU/graph.json","fetch_events":"https://pith.science/api/pith-number/MNMYYRL73V62RVFTUZ5OGANOFU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MNMYYRL73V62RVFTUZ5OGANOFU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MNMYYRL73V62RVFTUZ5OGANOFU/action/storage_attestation","attest_author":"https://pith.science/pith/MNMYYRL73V62RVFTUZ5OGANOFU/action/author_attestation","sign_citation":"https://pith.science/pith/MNMYYRL73V62RVFTUZ5OGANOFU/action/citation_signature","submit_replication":"https://pith.science/pith/MNMYYRL73V62RVFTUZ5OGANOFU/action/replication_record"}},"created_at":"2026-07-05T03:12:48.542822+00:00","updated_at":"2026-07-05T03:12:48.542822+00:00"}