{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:L4JNMSE3YH3XHJV5OICJSFRMY7","short_pith_number":"pith:L4JNMSE3","schema_version":"1.0","canonical_sha256":"5f12d6489bc1f773a6bd720499162cc7e9a2759190fa56ee57aa335adb34fe1e","source":{"kind":"arxiv","id":"2303.05186","version":1},"attestation_state":"computed","paper":{"title":"A Framework for History-Aware Hyperparameter Optimisation in Reinforcement Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.LG","authors_text":"Antonio Garc\\'ia-Dom\\'inguez, Changgang Zheng, Chen Zhen, Guadalupe Ortiz, Juan Boubeta-Puig, Juan Marcelo Parra-Ullauri, Nelly Bencomo, Shufan Yang","submitted_at":"2023-03-09T11:30:40Z","abstract_excerpt":"A Reinforcement Learning (RL) system depends on a set of initial conditions (hyperparameters) that affect the system's performance. However, defining a good choice of hyperparameters is a challenging problem.\n  Hyperparameter tuning often requires manual or automated searches to find optimal values. Nonetheless, a noticeable limitation is the high cost of algorithm evaluation for complex models, making the tuning process computationally expensive and time-consuming.\n  In this paper, we propose a framework based on integrating complex event processing and temporal models, to alleviate these tra"},"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":"2303.05186","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-09T11:30:40Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"89a62f95747f153b36dbcbb0aaa3822046e44aed896280aa1820094be793f415","abstract_canon_sha256":"cd5f665103a9c7eb0ed22e803698a05886c354a675c68b099bbd05427d96c5a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:38.195478Z","signature_b64":"pc2cKHVDp1ZCi7zey4uiozBF56ji4lPzwQOw4jG0S4L1HNx5MKdhULX/BKU7UwrBiqT4/cxOlv3cCr0CXuJWDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f12d6489bc1f773a6bd720499162cc7e9a2759190fa56ee57aa335adb34fe1e","last_reissued_at":"2026-07-05T05:49:38.195023Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:38.195023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Framework for History-Aware Hyperparameter Optimisation in Reinforcement Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.LG","authors_text":"Antonio Garc\\'ia-Dom\\'inguez, Changgang Zheng, Chen Zhen, Guadalupe Ortiz, Juan Boubeta-Puig, Juan Marcelo Parra-Ullauri, Nelly Bencomo, Shufan Yang","submitted_at":"2023-03-09T11:30:40Z","abstract_excerpt":"A Reinforcement Learning (RL) system depends on a set of initial conditions (hyperparameters) that affect the system's performance. However, defining a good choice of hyperparameters is a challenging problem.\n  Hyperparameter tuning often requires manual or automated searches to find optimal values. Nonetheless, a noticeable limitation is the high cost of algorithm evaluation for complex models, making the tuning process computationally expensive and time-consuming.\n  In this paper, we propose a framework based on integrating complex event processing and temporal models, to alleviate these tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.05186","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/2303.05186/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":"2303.05186","created_at":"2026-07-05T05:49:38.195082+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.05186v1","created_at":"2026-07-05T05:49:38.195082+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.05186","created_at":"2026-07-05T05:49:38.195082+00:00"},{"alias_kind":"pith_short_12","alias_value":"L4JNMSE3YH3X","created_at":"2026-07-05T05:49:38.195082+00:00"},{"alias_kind":"pith_short_16","alias_value":"L4JNMSE3YH3XHJV5","created_at":"2026-07-05T05:49:38.195082+00:00"},{"alias_kind":"pith_short_8","alias_value":"L4JNMSE3","created_at":"2026-07-05T05:49:38.195082+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/L4JNMSE3YH3XHJV5OICJSFRMY7","json":"https://pith.science/pith/L4JNMSE3YH3XHJV5OICJSFRMY7.json","graph_json":"https://pith.science/api/pith-number/L4JNMSE3YH3XHJV5OICJSFRMY7/graph.json","events_json":"https://pith.science/api/pith-number/L4JNMSE3YH3XHJV5OICJSFRMY7/events.json","paper":"https://pith.science/paper/L4JNMSE3"},"agent_actions":{"view_html":"https://pith.science/pith/L4JNMSE3YH3XHJV5OICJSFRMY7","download_json":"https://pith.science/pith/L4JNMSE3YH3XHJV5OICJSFRMY7.json","view_paper":"https://pith.science/paper/L4JNMSE3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.05186&json=true","fetch_graph":"https://pith.science/api/pith-number/L4JNMSE3YH3XHJV5OICJSFRMY7/graph.json","fetch_events":"https://pith.science/api/pith-number/L4JNMSE3YH3XHJV5OICJSFRMY7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L4JNMSE3YH3XHJV5OICJSFRMY7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L4JNMSE3YH3XHJV5OICJSFRMY7/action/storage_attestation","attest_author":"https://pith.science/pith/L4JNMSE3YH3XHJV5OICJSFRMY7/action/author_attestation","sign_citation":"https://pith.science/pith/L4JNMSE3YH3XHJV5OICJSFRMY7/action/citation_signature","submit_replication":"https://pith.science/pith/L4JNMSE3YH3XHJV5OICJSFRMY7/action/replication_record"}},"created_at":"2026-07-05T05:49:38.195082+00:00","updated_at":"2026-07-05T05:49:38.195082+00:00"}