{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ANZ7I2DE6YE7LAIO3MVSXQXRSP","short_pith_number":"pith:ANZ7I2DE","schema_version":"1.0","canonical_sha256":"0373f46864f609f5810edb2b2bc2f193cd4f02b0ca6a9384217e6ce315b97728","source":{"kind":"arxiv","id":"2006.07554","version":1},"attestation_state":"computed","paper":{"title":"Online Hyper-parameter Tuning in Off-policy Learning via Evolutionary Strategies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Krzysztof Choromanski, Yunhao Tang","submitted_at":"2020-06-13T03:54:26Z","abstract_excerpt":"Off-policy learning algorithms have been known to be sensitive to the choice of hyper-parameters. However, unlike near on-policy algorithms for which hyper-parameters could be optimized via e.g. meta-gradients, similar techniques could not be straightforwardly applied to off-policy learning. In this work, we propose a framework which entails the application of Evolutionary Strategies to online hyper-parameter tuning in off-policy learning. Our formulation draws close connections to meta-gradients and leverages the strengths of black-box optimization with relatively low-dimensional search space"},"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":"2006.07554","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-13T03:54:26Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"8090e9420c46794ef529222d0c3a818a11159dc3610dc098de2309c6ff265fe4","abstract_canon_sha256":"44b348b4d54f957d555efb7fe892d9376fc58a68a12f781a9cb74a9c3b6cff4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:10:01.255937Z","signature_b64":"kE8+M14HKgfF8FXPStyi+ct02kktjZvyuPANLlhiW2opgdxWyBR10agm4RaBzkfNhvR0b1vnz7svt4DSndclAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0373f46864f609f5810edb2b2bc2f193cd4f02b0ca6a9384217e6ce315b97728","last_reissued_at":"2026-07-05T01:10:01.255474Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:10:01.255474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Hyper-parameter Tuning in Off-policy Learning via Evolutionary Strategies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Krzysztof Choromanski, Yunhao Tang","submitted_at":"2020-06-13T03:54:26Z","abstract_excerpt":"Off-policy learning algorithms have been known to be sensitive to the choice of hyper-parameters. However, unlike near on-policy algorithms for which hyper-parameters could be optimized via e.g. meta-gradients, similar techniques could not be straightforwardly applied to off-policy learning. In this work, we propose a framework which entails the application of Evolutionary Strategies to online hyper-parameter tuning in off-policy learning. Our formulation draws close connections to meta-gradients and leverages the strengths of black-box optimization with relatively low-dimensional search space"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07554","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/2006.07554/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":"2006.07554","created_at":"2026-07-05T01:10:01.255533+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.07554v1","created_at":"2026-07-05T01:10:01.255533+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07554","created_at":"2026-07-05T01:10:01.255533+00:00"},{"alias_kind":"pith_short_12","alias_value":"ANZ7I2DE6YE7","created_at":"2026-07-05T01:10:01.255533+00:00"},{"alias_kind":"pith_short_16","alias_value":"ANZ7I2DE6YE7LAIO","created_at":"2026-07-05T01:10:01.255533+00:00"},{"alias_kind":"pith_short_8","alias_value":"ANZ7I2DE","created_at":"2026-07-05T01:10:01.255533+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.15129","citing_title":"EvoRL: A GPU-accelerated Framework for Evolutionary Reinforcement Learning","ref_index":2016,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ANZ7I2DE6YE7LAIO3MVSXQXRSP","json":"https://pith.science/pith/ANZ7I2DE6YE7LAIO3MVSXQXRSP.json","graph_json":"https://pith.science/api/pith-number/ANZ7I2DE6YE7LAIO3MVSXQXRSP/graph.json","events_json":"https://pith.science/api/pith-number/ANZ7I2DE6YE7LAIO3MVSXQXRSP/events.json","paper":"https://pith.science/paper/ANZ7I2DE"},"agent_actions":{"view_html":"https://pith.science/pith/ANZ7I2DE6YE7LAIO3MVSXQXRSP","download_json":"https://pith.science/pith/ANZ7I2DE6YE7LAIO3MVSXQXRSP.json","view_paper":"https://pith.science/paper/ANZ7I2DE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.07554&json=true","fetch_graph":"https://pith.science/api/pith-number/ANZ7I2DE6YE7LAIO3MVSXQXRSP/graph.json","fetch_events":"https://pith.science/api/pith-number/ANZ7I2DE6YE7LAIO3MVSXQXRSP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ANZ7I2DE6YE7LAIO3MVSXQXRSP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ANZ7I2DE6YE7LAIO3MVSXQXRSP/action/storage_attestation","attest_author":"https://pith.science/pith/ANZ7I2DE6YE7LAIO3MVSXQXRSP/action/author_attestation","sign_citation":"https://pith.science/pith/ANZ7I2DE6YE7LAIO3MVSXQXRSP/action/citation_signature","submit_replication":"https://pith.science/pith/ANZ7I2DE6YE7LAIO3MVSXQXRSP/action/replication_record"}},"created_at":"2026-07-05T01:10:01.255533+00:00","updated_at":"2026-07-05T01:10:01.255533+00:00"}