{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:CUO2WDJLMP4V2BCG3NAYBRLCGB","short_pith_number":"pith:CUO2WDJL","schema_version":"1.0","canonical_sha256":"151dab0d2b63f95d0446db4180c56230537cf9c10d0c1fd240e4ee4b4d4e5ba9","source":{"kind":"arxiv","id":"1602.04062","version":2},"attestation_state":"computed","paper":{"title":"Using Deep Q-Learning to Control Optimization Hyperparameters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Samantha Hansen","submitted_at":"2016-02-12T14:16:59Z","abstract_excerpt":"We present a novel definition of the reinforcement learning state, actions and reward function that allows a deep Q-network (DQN) to learn to control an optimization hyperparameter. Using Q-learning with experience replay, we train two DQNs to accept a state representation of an objective function as input and output the expected discounted return of rewards, or q-values, connected to the actions of either adjusting the learning rate or leaving it unchanged. The two DQNs learn a policy similar to a line search, but differ in the number of allowed actions. The trained DQNs in combination with a"},"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":"1602.04062","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-02-12T14:16:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cec570066e170e67b2f763d38b6614b9cde5fb789bee37731c55b030678426c5","abstract_canon_sha256":"8f3a2d9ac2baf29c462c94ade8143d8a689dbebd85f157d1775b9915bb9a907f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:16.793926Z","signature_b64":"O8rFnnlEZ99R9lNEav55bkw/6K73K/FGmHNKRWAeXO1E804QdlurY/7kaBGubn7wDcriwyf/Dqdx1znkadAgBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"151dab0d2b63f95d0446db4180c56230537cf9c10d0c1fd240e4ee4b4d4e5ba9","last_reissued_at":"2026-05-18T01:12:16.793580Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:16.793580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using Deep Q-Learning to Control Optimization Hyperparameters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Samantha Hansen","submitted_at":"2016-02-12T14:16:59Z","abstract_excerpt":"We present a novel definition of the reinforcement learning state, actions and reward function that allows a deep Q-network (DQN) to learn to control an optimization hyperparameter. Using Q-learning with experience replay, we train two DQNs to accept a state representation of an objective function as input and output the expected discounted return of rewards, or q-values, connected to the actions of either adjusting the learning rate or leaving it unchanged. The two DQNs learn a policy similar to a line search, but differ in the number of allowed actions. The trained DQNs in combination with a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.04062","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":""},"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":"1602.04062","created_at":"2026-05-18T01:12:16.793630+00:00"},{"alias_kind":"arxiv_version","alias_value":"1602.04062v2","created_at":"2026-05-18T01:12:16.793630+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.04062","created_at":"2026-05-18T01:12:16.793630+00:00"},{"alias_kind":"pith_short_12","alias_value":"CUO2WDJLMP4V","created_at":"2026-05-18T12:30:09.641336+00:00"},{"alias_kind":"pith_short_16","alias_value":"CUO2WDJLMP4V2BCG","created_at":"2026-05-18T12:30:09.641336+00:00"},{"alias_kind":"pith_short_8","alias_value":"CUO2WDJL","created_at":"2026-05-18T12:30:09.641336+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/CUO2WDJLMP4V2BCG3NAYBRLCGB","json":"https://pith.science/pith/CUO2WDJLMP4V2BCG3NAYBRLCGB.json","graph_json":"https://pith.science/api/pith-number/CUO2WDJLMP4V2BCG3NAYBRLCGB/graph.json","events_json":"https://pith.science/api/pith-number/CUO2WDJLMP4V2BCG3NAYBRLCGB/events.json","paper":"https://pith.science/paper/CUO2WDJL"},"agent_actions":{"view_html":"https://pith.science/pith/CUO2WDJLMP4V2BCG3NAYBRLCGB","download_json":"https://pith.science/pith/CUO2WDJLMP4V2BCG3NAYBRLCGB.json","view_paper":"https://pith.science/paper/CUO2WDJL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1602.04062&json=true","fetch_graph":"https://pith.science/api/pith-number/CUO2WDJLMP4V2BCG3NAYBRLCGB/graph.json","fetch_events":"https://pith.science/api/pith-number/CUO2WDJLMP4V2BCG3NAYBRLCGB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CUO2WDJLMP4V2BCG3NAYBRLCGB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CUO2WDJLMP4V2BCG3NAYBRLCGB/action/storage_attestation","attest_author":"https://pith.science/pith/CUO2WDJLMP4V2BCG3NAYBRLCGB/action/author_attestation","sign_citation":"https://pith.science/pith/CUO2WDJLMP4V2BCG3NAYBRLCGB/action/citation_signature","submit_replication":"https://pith.science/pith/CUO2WDJLMP4V2BCG3NAYBRLCGB/action/replication_record"}},"created_at":"2026-05-18T01:12:16.793630+00:00","updated_at":"2026-05-18T01:12:16.793630+00:00"}