{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3WDSBOP2Q2DKFYY53YYMXLVLCA","short_pith_number":"pith:3WDSBOP2","schema_version":"1.0","canonical_sha256":"dd8720b9fa8686a2e31dde30cbaeab103c5f955a8c1cde197826e2992aba3d30","source":{"kind":"arxiv","id":"2308.05711","version":1},"attestation_state":"computed","paper":{"title":"A Comparison of Classical and Deep Reinforcement Learning Methods for HVAC Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"John Willes, Marshall Wang, Matin Moezzi, Thomas Jiralerspong","submitted_at":"2023-08-10T17:20:02Z","abstract_excerpt":"Reinforcement learning (RL) is a promising approach for optimizing HVAC control. RL offers a framework for improving system performance, reducing energy consumption, and enhancing cost efficiency. We benchmark two popular classical and deep RL methods (Q-Learning and Deep-Q-Networks) across multiple HVAC environments and explore the practical consideration of model hyper-parameter selection and reward tuning. The findings provide insight for configuring RL agents in HVAC systems, promoting energy-efficient and cost-effective operation."},"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":"2308.05711","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-10T17:20:02Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"9f744d63cce945d6deace9db3287783fec6516c42c47e94eb56add08fe994033","abstract_canon_sha256":"c094b8d9d0d1766825847de615c499f082f2c75c1c6d7bc5c74f449b6726dfe7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:40:04.209663Z","signature_b64":"e7kaCNI3Qki23t6jkE0f/qfHMiuxGdhuMVCTc3IQRncpvuGVt+P6c4RkDPN5Y/wWRTvROT4ZVfyYUNbl8yXPAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd8720b9fa8686a2e31dde30cbaeab103c5f955a8c1cde197826e2992aba3d30","last_reissued_at":"2026-07-05T06:40:04.209185Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:40:04.209185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comparison of Classical and Deep Reinforcement Learning Methods for HVAC Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"John Willes, Marshall Wang, Matin Moezzi, Thomas Jiralerspong","submitted_at":"2023-08-10T17:20:02Z","abstract_excerpt":"Reinforcement learning (RL) is a promising approach for optimizing HVAC control. RL offers a framework for improving system performance, reducing energy consumption, and enhancing cost efficiency. We benchmark two popular classical and deep RL methods (Q-Learning and Deep-Q-Networks) across multiple HVAC environments and explore the practical consideration of model hyper-parameter selection and reward tuning. The findings provide insight for configuring RL agents in HVAC systems, promoting energy-efficient and cost-effective operation."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.05711","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/2308.05711/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":"2308.05711","created_at":"2026-07-05T06:40:04.209245+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.05711v1","created_at":"2026-07-05T06:40:04.209245+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.05711","created_at":"2026-07-05T06:40:04.209245+00:00"},{"alias_kind":"pith_short_12","alias_value":"3WDSBOP2Q2DK","created_at":"2026-07-05T06:40:04.209245+00:00"},{"alias_kind":"pith_short_16","alias_value":"3WDSBOP2Q2DKFYY5","created_at":"2026-07-05T06:40:04.209245+00:00"},{"alias_kind":"pith_short_8","alias_value":"3WDSBOP2","created_at":"2026-07-05T06:40:04.209245+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.08293","citing_title":"SINERGYM -- A virtual testbed for building energy optimization with Reinforcement Learning","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3WDSBOP2Q2DKFYY53YYMXLVLCA","json":"https://pith.science/pith/3WDSBOP2Q2DKFYY53YYMXLVLCA.json","graph_json":"https://pith.science/api/pith-number/3WDSBOP2Q2DKFYY53YYMXLVLCA/graph.json","events_json":"https://pith.science/api/pith-number/3WDSBOP2Q2DKFYY53YYMXLVLCA/events.json","paper":"https://pith.science/paper/3WDSBOP2"},"agent_actions":{"view_html":"https://pith.science/pith/3WDSBOP2Q2DKFYY53YYMXLVLCA","download_json":"https://pith.science/pith/3WDSBOP2Q2DKFYY53YYMXLVLCA.json","view_paper":"https://pith.science/paper/3WDSBOP2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.05711&json=true","fetch_graph":"https://pith.science/api/pith-number/3WDSBOP2Q2DKFYY53YYMXLVLCA/graph.json","fetch_events":"https://pith.science/api/pith-number/3WDSBOP2Q2DKFYY53YYMXLVLCA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3WDSBOP2Q2DKFYY53YYMXLVLCA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3WDSBOP2Q2DKFYY53YYMXLVLCA/action/storage_attestation","attest_author":"https://pith.science/pith/3WDSBOP2Q2DKFYY53YYMXLVLCA/action/author_attestation","sign_citation":"https://pith.science/pith/3WDSBOP2Q2DKFYY53YYMXLVLCA/action/citation_signature","submit_replication":"https://pith.science/pith/3WDSBOP2Q2DKFYY53YYMXLVLCA/action/replication_record"}},"created_at":"2026-07-05T06:40:04.209245+00:00","updated_at":"2026-07-05T06:40:04.209245+00:00"}