{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OSUGZGQOWGEVLLRD4L6KJM35RN","short_pith_number":"pith:OSUGZGQO","schema_version":"1.0","canonical_sha256":"74a86c9a0eb18955ae23e2fca4b37d8b512fde7c2c54c05b708f5e5682b17ef5","source":{"kind":"arxiv","id":"2512.03805","version":2},"attestation_state":"computed","paper":{"title":"Deep Reinforcement Learning for Dynamic Algorithm Configuration: A Case Study on Optimizing OneMax with the (1+($\\lambda$,$\\lambda$))-GA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andr\\'e Biedenkapp, Carola Doerr, Nguyen Dang, Phong Le, Tai Nguyen","submitted_at":"2025-12-03T13:54:41Z","abstract_excerpt":"Dynamic Algorithm Configuration (DAC) studies the efficient identification of control policies for parameterized optimization algorithms. Numerous studies leverage Reinforcement Learning (RL) to address DAC challenges; however, applying RL often requires extensive domain expertise. In this work, we conduct a comprehensive study of two deep-RL algorithms--Double Deep Q-Networks (DDQN) and Proximal Policy Optimization (PPO)--for controlling the population size of the $(1+(\\lambda,\\lambda))$-GA on OneMax instances. Although OneMax is structurally simple, learning effective control policies for th"},"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":"2512.03805","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-03T13:54:41Z","cross_cats_sorted":[],"title_canon_sha256":"b613de6ddc12815a3a9ed625f89e1e966e367fa3e8f2791e5083600f9b04ea43","abstract_canon_sha256":"49cea4c419be0d3e47a20d307e325ee5984f9a3217313d810fabb3d3d5dbeb30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:33.037994Z","signature_b64":"icHQk+6cznsVYWjVfDmZN+sKQmrIhdgAza5ZwZLyZG2nUlIyMiHpjAcjEUwOPoOOGgYWwpu8x6GnkdoSssP6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74a86c9a0eb18955ae23e2fca4b37d8b512fde7c2c54c05b708f5e5682b17ef5","last_reissued_at":"2026-06-19T16:10:33.037467Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:33.037467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning for Dynamic Algorithm Configuration: A Case Study on Optimizing OneMax with the (1+($\\lambda$,$\\lambda$))-GA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andr\\'e Biedenkapp, Carola Doerr, Nguyen Dang, Phong Le, Tai Nguyen","submitted_at":"2025-12-03T13:54:41Z","abstract_excerpt":"Dynamic Algorithm Configuration (DAC) studies the efficient identification of control policies for parameterized optimization algorithms. Numerous studies leverage Reinforcement Learning (RL) to address DAC challenges; however, applying RL often requires extensive domain expertise. In this work, we conduct a comprehensive study of two deep-RL algorithms--Double Deep Q-Networks (DDQN) and Proximal Policy Optimization (PPO)--for controlling the population size of the $(1+(\\lambda,\\lambda))$-GA on OneMax instances. Although OneMax is structurally simple, learning effective control policies for th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.03805","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/2512.03805/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":"2512.03805","created_at":"2026-06-19T16:10:33.037534+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.03805v2","created_at":"2026-06-19T16:10:33.037534+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.03805","created_at":"2026-06-19T16:10:33.037534+00:00"},{"alias_kind":"pith_short_12","alias_value":"OSUGZGQOWGEV","created_at":"2026-06-19T16:10:33.037534+00:00"},{"alias_kind":"pith_short_16","alias_value":"OSUGZGQOWGEVLLRD","created_at":"2026-06-19T16:10:33.037534+00:00"},{"alias_kind":"pith_short_8","alias_value":"OSUGZGQO","created_at":"2026-06-19T16:10:33.037534+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.10129","citing_title":"Discovering Interpretable Multi-Parameter Control Policies for Evolutionary Algorithms Using Deep Reinforcement Learning","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OSUGZGQOWGEVLLRD4L6KJM35RN","json":"https://pith.science/pith/OSUGZGQOWGEVLLRD4L6KJM35RN.json","graph_json":"https://pith.science/api/pith-number/OSUGZGQOWGEVLLRD4L6KJM35RN/graph.json","events_json":"https://pith.science/api/pith-number/OSUGZGQOWGEVLLRD4L6KJM35RN/events.json","paper":"https://pith.science/paper/OSUGZGQO"},"agent_actions":{"view_html":"https://pith.science/pith/OSUGZGQOWGEVLLRD4L6KJM35RN","download_json":"https://pith.science/pith/OSUGZGQOWGEVLLRD4L6KJM35RN.json","view_paper":"https://pith.science/paper/OSUGZGQO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.03805&json=true","fetch_graph":"https://pith.science/api/pith-number/OSUGZGQOWGEVLLRD4L6KJM35RN/graph.json","fetch_events":"https://pith.science/api/pith-number/OSUGZGQOWGEVLLRD4L6KJM35RN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OSUGZGQOWGEVLLRD4L6KJM35RN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OSUGZGQOWGEVLLRD4L6KJM35RN/action/storage_attestation","attest_author":"https://pith.science/pith/OSUGZGQOWGEVLLRD4L6KJM35RN/action/author_attestation","sign_citation":"https://pith.science/pith/OSUGZGQOWGEVLLRD4L6KJM35RN/action/citation_signature","submit_replication":"https://pith.science/pith/OSUGZGQOWGEVLLRD4L6KJM35RN/action/replication_record"}},"created_at":"2026-06-19T16:10:33.037534+00:00","updated_at":"2026-06-19T16:10:33.037534+00:00"}