{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:B5WXPQFT6HOPD7WAPRV22YV7XU","short_pith_number":"pith:B5WXPQFT","schema_version":"1.0","canonical_sha256":"0f6d77c0b3f1dcf1fec07c6bad62bfbd179b83ac676dfd49080cff5d1ba4ad78","source":{"kind":"arxiv","id":"2111.11987","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning for Volt-Var Control: A Novel Two-stage Progressive Training Strategy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"David Lubkeman, Mingzhi Zhang, Ning Lu, Rongxing Hu, Si Zhang, Yunan Liu","submitted_at":"2021-11-23T16:33:22Z","abstract_excerpt":"This paper develops a reinforcement learning (RL)approach to solve a cooperative, multi-agent Volt-Var Control (VVC) problem for high solar penetration distribution systems. The ingenuity of our RL method lies in a novel two-stage progressive training strategy that can effectively improve training speed and convergence of the machine learning algorithm. In Stage 1(individual training), while holding all the other agents inactive, we separately train each agent to obtain its own optimal VVC actions in the action space: {consume, generate, do-nothing}. In Stage 2 (cooperative training), all agen"},"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":"2111.11987","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2021-11-23T16:33:22Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"87396d62c66d5d9f4d3a6a9b47b4288f19fb83eb18f35bc01dd5ae559ed50b26","abstract_canon_sha256":"5b036d7fd6e11743e69b6d8dc638c5a8439c4f81962053a4d500e31d1d679992"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:34:39.563165Z","signature_b64":"nYyqzzQDSU3EJwrjek0hmE1wEVIcHzVfsCivBcCiEGPdF6oWmDiDPm651a0HDTigCKhJdR0OsT1W6Fz5ly1nAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f6d77c0b3f1dcf1fec07c6bad62bfbd179b83ac676dfd49080cff5d1ba4ad78","last_reissued_at":"2026-07-05T03:34:39.562827Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:34:39.562827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning for Volt-Var Control: A Novel Two-stage Progressive Training Strategy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"David Lubkeman, Mingzhi Zhang, Ning Lu, Rongxing Hu, Si Zhang, Yunan Liu","submitted_at":"2021-11-23T16:33:22Z","abstract_excerpt":"This paper develops a reinforcement learning (RL)approach to solve a cooperative, multi-agent Volt-Var Control (VVC) problem for high solar penetration distribution systems. The ingenuity of our RL method lies in a novel two-stage progressive training strategy that can effectively improve training speed and convergence of the machine learning algorithm. In Stage 1(individual training), while holding all the other agents inactive, we separately train each agent to obtain its own optimal VVC actions in the action space: {consume, generate, do-nothing}. In Stage 2 (cooperative training), all agen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.11987","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/2111.11987/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":"2111.11987","created_at":"2026-07-05T03:34:39.562884+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.11987v1","created_at":"2026-07-05T03:34:39.562884+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.11987","created_at":"2026-07-05T03:34:39.562884+00:00"},{"alias_kind":"pith_short_12","alias_value":"B5WXPQFT6HOP","created_at":"2026-07-05T03:34:39.562884+00:00"},{"alias_kind":"pith_short_16","alias_value":"B5WXPQFT6HOPD7WA","created_at":"2026-07-05T03:34:39.562884+00:00"},{"alias_kind":"pith_short_8","alias_value":"B5WXPQFT","created_at":"2026-07-05T03:34:39.562884+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B5WXPQFT6HOPD7WAPRV22YV7XU","json":"https://pith.science/pith/B5WXPQFT6HOPD7WAPRV22YV7XU.json","graph_json":"https://pith.science/api/pith-number/B5WXPQFT6HOPD7WAPRV22YV7XU/graph.json","events_json":"https://pith.science/api/pith-number/B5WXPQFT6HOPD7WAPRV22YV7XU/events.json","paper":"https://pith.science/paper/B5WXPQFT"},"agent_actions":{"view_html":"https://pith.science/pith/B5WXPQFT6HOPD7WAPRV22YV7XU","download_json":"https://pith.science/pith/B5WXPQFT6HOPD7WAPRV22YV7XU.json","view_paper":"https://pith.science/paper/B5WXPQFT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.11987&json=true","fetch_graph":"https://pith.science/api/pith-number/B5WXPQFT6HOPD7WAPRV22YV7XU/graph.json","fetch_events":"https://pith.science/api/pith-number/B5WXPQFT6HOPD7WAPRV22YV7XU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B5WXPQFT6HOPD7WAPRV22YV7XU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B5WXPQFT6HOPD7WAPRV22YV7XU/action/storage_attestation","attest_author":"https://pith.science/pith/B5WXPQFT6HOPD7WAPRV22YV7XU/action/author_attestation","sign_citation":"https://pith.science/pith/B5WXPQFT6HOPD7WAPRV22YV7XU/action/citation_signature","submit_replication":"https://pith.science/pith/B5WXPQFT6HOPD7WAPRV22YV7XU/action/replication_record"}},"created_at":"2026-07-05T03:34:39.562884+00:00","updated_at":"2026-07-05T03:34:39.562884+00:00"}