{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:T22TBYHW2K2ILCE3H6XENC6RNV","short_pith_number":"pith:T22TBYHW","schema_version":"1.0","canonical_sha256":"9eb530e0f6d2b485889b3fae468bd16d6e173a4b48068d4bbb662772bfa026d9","source":{"kind":"arxiv","id":"2302.00725","version":1},"attestation_state":"computed","paper":{"title":"Multi-zone HVAC Control with Model-Based Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Alberto Cerpa, Wan Du, Xianzhong Ding","submitted_at":"2023-02-01T19:41:03Z","abstract_excerpt":"In this paper, we conduct a set of experiments to analyze the limitations of current MBRL-based HVAC control methods, in terms of model uncertainty and controller effectiveness. Using the lessons learned, we develop MB2C, a novel MBRL-based HVAC control system that can achieve high control performance with excellent sample efficiency. MB2C learns the building dynamics by employing an ensemble of environment-conditioned neural networks. It then applies a new control method, Model Predictive Path Integral (MPPI), for HVAC control. It produces candidate action sequences by using an importance sam"},"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":"2302.00725","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2023-02-01T19:41:03Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"0e644ccdfec67c99081462557e925519da14cf4e37ca9d696dc35a69e7d292a5","abstract_canon_sha256":"ec55a4b506f6083f622b027ffad676a45e362d9b97988a63987608ef065ca155"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:38:11.552851Z","signature_b64":"k7iXyK4Y0QHh3ZECWOiKYoSKm58wQlZjVPtmKOFvv2i9x7ajZyLhlGkpb9g3ta5Evkgr51PjjD1XfnGrwQbrDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9eb530e0f6d2b485889b3fae468bd16d6e173a4b48068d4bbb662772bfa026d9","last_reissued_at":"2026-07-05T05:38:11.552459Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:38:11.552459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-zone HVAC Control with Model-Based Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Alberto Cerpa, Wan Du, Xianzhong Ding","submitted_at":"2023-02-01T19:41:03Z","abstract_excerpt":"In this paper, we conduct a set of experiments to analyze the limitations of current MBRL-based HVAC control methods, in terms of model uncertainty and controller effectiveness. Using the lessons learned, we develop MB2C, a novel MBRL-based HVAC control system that can achieve high control performance with excellent sample efficiency. MB2C learns the building dynamics by employing an ensemble of environment-conditioned neural networks. It then applies a new control method, Model Predictive Path Integral (MPPI), for HVAC control. It produces candidate action sequences by using an importance sam"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.00725","kind":"arxiv","version":1},"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/2302.00725/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":"2302.00725","created_at":"2026-07-05T05:38:11.552516+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.00725v1","created_at":"2026-07-05T05:38:11.552516+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.00725","created_at":"2026-07-05T05:38:11.552516+00:00"},{"alias_kind":"pith_short_12","alias_value":"T22TBYHW2K2I","created_at":"2026-07-05T05:38:11.552516+00:00"},{"alias_kind":"pith_short_16","alias_value":"T22TBYHW2K2ILCE3","created_at":"2026-07-05T05:38:11.552516+00:00"},{"alias_kind":"pith_short_8","alias_value":"T22TBYHW","created_at":"2026-07-05T05:38:11.552516+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.11324","citing_title":"Contextual Quality-Diversity Evolutionary Reinforcement Learning for HVAC Control in Tropical Commercial Buildings","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T22TBYHW2K2ILCE3H6XENC6RNV","json":"https://pith.science/pith/T22TBYHW2K2ILCE3H6XENC6RNV.json","graph_json":"https://pith.science/api/pith-number/T22TBYHW2K2ILCE3H6XENC6RNV/graph.json","events_json":"https://pith.science/api/pith-number/T22TBYHW2K2ILCE3H6XENC6RNV/events.json","paper":"https://pith.science/paper/T22TBYHW"},"agent_actions":{"view_html":"https://pith.science/pith/T22TBYHW2K2ILCE3H6XENC6RNV","download_json":"https://pith.science/pith/T22TBYHW2K2ILCE3H6XENC6RNV.json","view_paper":"https://pith.science/paper/T22TBYHW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.00725&json=true","fetch_graph":"https://pith.science/api/pith-number/T22TBYHW2K2ILCE3H6XENC6RNV/graph.json","fetch_events":"https://pith.science/api/pith-number/T22TBYHW2K2ILCE3H6XENC6RNV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T22TBYHW2K2ILCE3H6XENC6RNV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T22TBYHW2K2ILCE3H6XENC6RNV/action/storage_attestation","attest_author":"https://pith.science/pith/T22TBYHW2K2ILCE3H6XENC6RNV/action/author_attestation","sign_citation":"https://pith.science/pith/T22TBYHW2K2ILCE3H6XENC6RNV/action/citation_signature","submit_replication":"https://pith.science/pith/T22TBYHW2K2ILCE3H6XENC6RNV/action/replication_record"}},"created_at":"2026-07-05T05:38:11.552516+00:00","updated_at":"2026-07-05T05:38:11.552516+00:00"}