{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZYXPHTLQLBPZA4KNCMJTABW5WH","short_pith_number":"pith:ZYXPHTLQ","schema_version":"1.0","canonical_sha256":"ce2ef3cd70585f90714d13133006ddb1ec0043c219de254325542ddc179ad74c","source":{"kind":"arxiv","id":"2112.04084","version":1},"attestation_state":"computed","paper":{"title":"Hyper-parameter optimization based on soft actor critic and hierarchical mixture regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chaoyue Liu, Yulai Zhang","submitted_at":"2021-12-08T02:34:43Z","abstract_excerpt":"Hyper-parameter optimization is a crucial problem in machine learning as it aims to achieve the state-of-the-art performance in any model. Great efforts have been made in this field, such as random search, grid search, Bayesian optimization. In this paper, we model hyper-parameter optimization process as a Markov decision process, and tackle it with reinforcement learning. A novel hyper-parameter optimization method based on soft actor critic and hierarchical mixture regularization has been proposed. Experiments show that the proposed method can obtain better hyper-parameters in a shorter time"},"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":"2112.04084","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-08T02:34:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fbccb03ff91cdf625c84b636535316afd4383c16b41ae127a84780f9d9ba97d2","abstract_canon_sha256":"8033e72840b1f79d216aef59dd47564059a34e081e8f3ebc993d2e6d28a01f57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:39:05.831239Z","signature_b64":"2H2UlO8liKj7l4iJ6wLl1HizRyQ1zFVUcsahAwxKoaowJSs27VN2eOT9dpx0MCTHN82vWYbvQBJeQpOS4mI6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce2ef3cd70585f90714d13133006ddb1ec0043c219de254325542ddc179ad74c","last_reissued_at":"2026-07-05T03:39:05.830899Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:39:05.830899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hyper-parameter optimization based on soft actor critic and hierarchical mixture regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chaoyue Liu, Yulai Zhang","submitted_at":"2021-12-08T02:34:43Z","abstract_excerpt":"Hyper-parameter optimization is a crucial problem in machine learning as it aims to achieve the state-of-the-art performance in any model. Great efforts have been made in this field, such as random search, grid search, Bayesian optimization. In this paper, we model hyper-parameter optimization process as a Markov decision process, and tackle it with reinforcement learning. A novel hyper-parameter optimization method based on soft actor critic and hierarchical mixture regularization has been proposed. Experiments show that the proposed method can obtain better hyper-parameters in a shorter time"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.04084","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/2112.04084/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":"2112.04084","created_at":"2026-07-05T03:39:05.830955+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.04084v1","created_at":"2026-07-05T03:39:05.830955+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.04084","created_at":"2026-07-05T03:39:05.830955+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZYXPHTLQLBPZ","created_at":"2026-07-05T03:39:05.830955+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZYXPHTLQLBPZA4KN","created_at":"2026-07-05T03:39:05.830955+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZYXPHTLQ","created_at":"2026-07-05T03:39:05.830955+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22443","citing_title":"Frequency Resource Management in 6G User-Centric CFmMIMO: A Hybrid Reinforcement Learning and Metaheuristic Approach","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZYXPHTLQLBPZA4KNCMJTABW5WH","json":"https://pith.science/pith/ZYXPHTLQLBPZA4KNCMJTABW5WH.json","graph_json":"https://pith.science/api/pith-number/ZYXPHTLQLBPZA4KNCMJTABW5WH/graph.json","events_json":"https://pith.science/api/pith-number/ZYXPHTLQLBPZA4KNCMJTABW5WH/events.json","paper":"https://pith.science/paper/ZYXPHTLQ"},"agent_actions":{"view_html":"https://pith.science/pith/ZYXPHTLQLBPZA4KNCMJTABW5WH","download_json":"https://pith.science/pith/ZYXPHTLQLBPZA4KNCMJTABW5WH.json","view_paper":"https://pith.science/paper/ZYXPHTLQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.04084&json=true","fetch_graph":"https://pith.science/api/pith-number/ZYXPHTLQLBPZA4KNCMJTABW5WH/graph.json","fetch_events":"https://pith.science/api/pith-number/ZYXPHTLQLBPZA4KNCMJTABW5WH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZYXPHTLQLBPZA4KNCMJTABW5WH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZYXPHTLQLBPZA4KNCMJTABW5WH/action/storage_attestation","attest_author":"https://pith.science/pith/ZYXPHTLQLBPZA4KNCMJTABW5WH/action/author_attestation","sign_citation":"https://pith.science/pith/ZYXPHTLQLBPZA4KNCMJTABW5WH/action/citation_signature","submit_replication":"https://pith.science/pith/ZYXPHTLQLBPZA4KNCMJTABW5WH/action/replication_record"}},"created_at":"2026-07-05T03:39:05.830955+00:00","updated_at":"2026-07-05T03:39:05.830955+00:00"}