{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2Z5FRBVQVWLMMCLP5DF4D7SL7A","short_pith_number":"pith:2Z5FRBVQ","schema_version":"1.0","canonical_sha256":"d67a5886b0ad96c6096fe8cbc1fe4bf82867240dece097c6965570f47802534c","source":{"kind":"arxiv","id":"2505.07832","version":1},"attestation_state":"computed","paper":{"title":"A General Approach of Automated Environment Design for Learning the Optimal Power Flow","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Astrid Nie{\\ss}e, Thomas Wolgast","submitted_at":"2025-05-01T11:02:55Z","abstract_excerpt":"Reinforcement learning (RL) algorithms are increasingly used to solve the optimal power flow (OPF) problem. Yet, the question of how to design RL environments to maximize training performance remains unanswered, both for the OPF and the general case. We propose a general approach for automated RL environment design by utilizing multi-objective optimization. For that, we use the hyperparameter optimization (HPO) framework, which allows the reuse of existing HPO algorithms and methods. On five OPF benchmark problems, we demonstrate that our automated design approach consistently outperforms a ma"},"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":"2505.07832","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-01T11:02:55Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"title_canon_sha256":"0f141f0df325ca5cce441fa9b87ac68522da98d3a7c5753ac1ac72fea51e5972","abstract_canon_sha256":"f65dbed5179358d34f40114299188c70603de06525af8dd3a6658f4398a3ce2a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:57.714619Z","signature_b64":"J8RJXssNv7jWzt7I4ESQHDD5z2d4DPWMxo+YKK6ToYQNAOtDuPWwnPSENRHBUSVEPCGkIzhEoInvykkOoxJQAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d67a5886b0ad96c6096fe8cbc1fe4bf82867240dece097c6965570f47802534c","last_reissued_at":"2026-07-05T11:01:57.714169Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:57.714169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A General Approach of Automated Environment Design for Learning the Optimal Power Flow","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Astrid Nie{\\ss}e, Thomas Wolgast","submitted_at":"2025-05-01T11:02:55Z","abstract_excerpt":"Reinforcement learning (RL) algorithms are increasingly used to solve the optimal power flow (OPF) problem. Yet, the question of how to design RL environments to maximize training performance remains unanswered, both for the OPF and the general case. We propose a general approach for automated RL environment design by utilizing multi-objective optimization. For that, we use the hyperparameter optimization (HPO) framework, which allows the reuse of existing HPO algorithms and methods. On five OPF benchmark problems, we demonstrate that our automated design approach consistently outperforms a ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07832","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/2505.07832/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":"2505.07832","created_at":"2026-07-05T11:01:57.714229+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.07832v1","created_at":"2026-07-05T11:01:57.714229+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07832","created_at":"2026-07-05T11:01:57.714229+00:00"},{"alias_kind":"pith_short_12","alias_value":"2Z5FRBVQVWLM","created_at":"2026-07-05T11:01:57.714229+00:00"},{"alias_kind":"pith_short_16","alias_value":"2Z5FRBVQVWLMMCLP","created_at":"2026-07-05T11:01:57.714229+00:00"},{"alias_kind":"pith_short_8","alias_value":"2Z5FRBVQ","created_at":"2026-07-05T11:01:57.714229+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/2Z5FRBVQVWLMMCLP5DF4D7SL7A","json":"https://pith.science/pith/2Z5FRBVQVWLMMCLP5DF4D7SL7A.json","graph_json":"https://pith.science/api/pith-number/2Z5FRBVQVWLMMCLP5DF4D7SL7A/graph.json","events_json":"https://pith.science/api/pith-number/2Z5FRBVQVWLMMCLP5DF4D7SL7A/events.json","paper":"https://pith.science/paper/2Z5FRBVQ"},"agent_actions":{"view_html":"https://pith.science/pith/2Z5FRBVQVWLMMCLP5DF4D7SL7A","download_json":"https://pith.science/pith/2Z5FRBVQVWLMMCLP5DF4D7SL7A.json","view_paper":"https://pith.science/paper/2Z5FRBVQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.07832&json=true","fetch_graph":"https://pith.science/api/pith-number/2Z5FRBVQVWLMMCLP5DF4D7SL7A/graph.json","fetch_events":"https://pith.science/api/pith-number/2Z5FRBVQVWLMMCLP5DF4D7SL7A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2Z5FRBVQVWLMMCLP5DF4D7SL7A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2Z5FRBVQVWLMMCLP5DF4D7SL7A/action/storage_attestation","attest_author":"https://pith.science/pith/2Z5FRBVQVWLMMCLP5DF4D7SL7A/action/author_attestation","sign_citation":"https://pith.science/pith/2Z5FRBVQVWLMMCLP5DF4D7SL7A/action/citation_signature","submit_replication":"https://pith.science/pith/2Z5FRBVQVWLMMCLP5DF4D7SL7A/action/replication_record"}},"created_at":"2026-07-05T11:01:57.714229+00:00","updated_at":"2026-07-05T11:01:57.714229+00:00"}