{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WG64SBERZUWIBNZDPS76BHFJ4T","short_pith_number":"pith:WG64SBER","schema_version":"1.0","canonical_sha256":"b1bdc90491cd2c80b7237cbfe09ca9e4cc55628dbf4e3110e9a5114e5725ca88","source":{"kind":"arxiv","id":"2202.10464","version":1},"attestation_state":"computed","paper":{"title":"A Globally Convergent Evolutionary Strategy for Stochastic Constrained Optimization with Applications to Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.OC","stat.ML"],"primary_cat":"cs.NE","authors_text":"Aurelien Lucchi, Vihang Patil, Youssef Diouane","submitted_at":"2022-02-21T17:04:51Z","abstract_excerpt":"Evolutionary strategies have recently been shown to achieve competing levels of performance for complex optimization problems in reinforcement learning. In such problems, one often needs to optimize an objective function subject to a set of constraints, including for instance constraints on the entropy of a policy or to restrict the possible set of actions or states accessible to an agent. Convergence guarantees for evolutionary strategies to optimize stochastic constrained problems are however lacking in the literature. In this work, we address this problem by designing a novel optimization 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":"2202.10464","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2022-02-21T17:04:51Z","cross_cats_sorted":["cs.LG","math.OC","stat.ML"],"title_canon_sha256":"d94a6ef61a93bfb18b1264f1e69c923a9c588b0b7ffd960c0b1fe38d297f7da7","abstract_canon_sha256":"ff4eee08c7b14069b62b3e3bc0e8a37dd2e61d506bad99f138900bd422ac7aba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:59:04.829437Z","signature_b64":"g9ZdFjC0qE55Bs+VxKB+syl3Rud5knXILpNTEHPMDJlQxrh+UXOzoqVeNqbkb7tDAy24oVMQW2kdXXPIpbEzBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1bdc90491cd2c80b7237cbfe09ca9e4cc55628dbf4e3110e9a5114e5725ca88","last_reissued_at":"2026-07-05T03:59:04.828952Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:59:04.828952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Globally Convergent Evolutionary Strategy for Stochastic Constrained Optimization with Applications to Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.OC","stat.ML"],"primary_cat":"cs.NE","authors_text":"Aurelien Lucchi, Vihang Patil, Youssef Diouane","submitted_at":"2022-02-21T17:04:51Z","abstract_excerpt":"Evolutionary strategies have recently been shown to achieve competing levels of performance for complex optimization problems in reinforcement learning. In such problems, one often needs to optimize an objective function subject to a set of constraints, including for instance constraints on the entropy of a policy or to restrict the possible set of actions or states accessible to an agent. Convergence guarantees for evolutionary strategies to optimize stochastic constrained problems are however lacking in the literature. In this work, we address this problem by designing a novel optimization a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.10464","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/2202.10464/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":"2202.10464","created_at":"2026-07-05T03:59:04.829011+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.10464v1","created_at":"2026-07-05T03:59:04.829011+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.10464","created_at":"2026-07-05T03:59:04.829011+00:00"},{"alias_kind":"pith_short_12","alias_value":"WG64SBERZUWI","created_at":"2026-07-05T03:59:04.829011+00:00"},{"alias_kind":"pith_short_16","alias_value":"WG64SBERZUWIBNZD","created_at":"2026-07-05T03:59:04.829011+00:00"},{"alias_kind":"pith_short_8","alias_value":"WG64SBER","created_at":"2026-07-05T03:59:04.829011+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/WG64SBERZUWIBNZDPS76BHFJ4T","json":"https://pith.science/pith/WG64SBERZUWIBNZDPS76BHFJ4T.json","graph_json":"https://pith.science/api/pith-number/WG64SBERZUWIBNZDPS76BHFJ4T/graph.json","events_json":"https://pith.science/api/pith-number/WG64SBERZUWIBNZDPS76BHFJ4T/events.json","paper":"https://pith.science/paper/WG64SBER"},"agent_actions":{"view_html":"https://pith.science/pith/WG64SBERZUWIBNZDPS76BHFJ4T","download_json":"https://pith.science/pith/WG64SBERZUWIBNZDPS76BHFJ4T.json","view_paper":"https://pith.science/paper/WG64SBER","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.10464&json=true","fetch_graph":"https://pith.science/api/pith-number/WG64SBERZUWIBNZDPS76BHFJ4T/graph.json","fetch_events":"https://pith.science/api/pith-number/WG64SBERZUWIBNZDPS76BHFJ4T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WG64SBERZUWIBNZDPS76BHFJ4T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WG64SBERZUWIBNZDPS76BHFJ4T/action/storage_attestation","attest_author":"https://pith.science/pith/WG64SBERZUWIBNZDPS76BHFJ4T/action/author_attestation","sign_citation":"https://pith.science/pith/WG64SBERZUWIBNZDPS76BHFJ4T/action/citation_signature","submit_replication":"https://pith.science/pith/WG64SBERZUWIBNZDPS76BHFJ4T/action/replication_record"}},"created_at":"2026-07-05T03:59:04.829011+00:00","updated_at":"2026-07-05T03:59:04.829011+00:00"}