{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:WVSXG3RXX7SZR3OO5ZQGTFZSRJ","short_pith_number":"pith:WVSXG3RX","schema_version":"1.0","canonical_sha256":"b565736e37bfe598edceee606997328a63b2c88aeddbff9fd58da46814fcc466","source":{"kind":"arxiv","id":"2002.05368","version":2},"attestation_state":"computed","paper":{"title":"Effective Reinforcement Learning through Evolutionary Surrogate-Assisted Prescription","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Babak Hodjat, Elliot Meyerson, Hormoz Shahrzad, Olivier Francon, Risto Miikkulainen, Santiago Gonzalez, Xin Qiu","submitted_at":"2020-02-13T06:59:26Z","abstract_excerpt":"There is now significant historical data available on decision making in organizations, consisting of the decision problem, what decisions were made, and how desirable the outcomes were. Using this data, it is possible to learn a surrogate model, and with that model, evolve a decision strategy that optimizes the outcomes. This paper introduces a general such approach, called Evolutionary Surrogate-Assisted Prescription, or ESP. The surrogate is, for example, a random forest or a neural network trained with gradient descent, and the strategy is a neural network that is evolved to maximize the p"},"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":"2002.05368","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2020-02-13T06:59:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"efd3deef2e695ce09cd80452b81b0e4f036300edbeb97c4643a821a4e3316ed8","abstract_canon_sha256":"3920da9d61cf8f87cea786ec4c47e544ce2964751c014e829ce332f4b0950212"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:57:25.328365Z","signature_b64":"SUdhaDXP70UVOUWm7No1NA+a1jnvmN0MbvSezsrNDH2stkAfArzRaDnW/1Wfdd9t8Z7gUP/908Ax1gFo2fEGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b565736e37bfe598edceee606997328a63b2c88aeddbff9fd58da46814fcc466","last_reissued_at":"2026-07-05T00:57:25.327874Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:57:25.327874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Effective Reinforcement Learning through Evolutionary Surrogate-Assisted Prescription","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Babak Hodjat, Elliot Meyerson, Hormoz Shahrzad, Olivier Francon, Risto Miikkulainen, Santiago Gonzalez, Xin Qiu","submitted_at":"2020-02-13T06:59:26Z","abstract_excerpt":"There is now significant historical data available on decision making in organizations, consisting of the decision problem, what decisions were made, and how desirable the outcomes were. Using this data, it is possible to learn a surrogate model, and with that model, evolve a decision strategy that optimizes the outcomes. This paper introduces a general such approach, called Evolutionary Surrogate-Assisted Prescription, or ESP. The surrogate is, for example, a random forest or a neural network trained with gradient descent, and the strategy is a neural network that is evolved to maximize the p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.05368","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2002.05368/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":"2002.05368","created_at":"2026-07-05T00:57:25.327939+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.05368v2","created_at":"2026-07-05T00:57:25.327939+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.05368","created_at":"2026-07-05T00:57:25.327939+00:00"},{"alias_kind":"pith_short_12","alias_value":"WVSXG3RXX7SZ","created_at":"2026-07-05T00:57:25.327939+00:00"},{"alias_kind":"pith_short_16","alias_value":"WVSXG3RXX7SZR3OO","created_at":"2026-07-05T00:57:25.327939+00:00"},{"alias_kind":"pith_short_8","alias_value":"WVSXG3RX","created_at":"2026-07-05T00:57:25.327939+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.12568","citing_title":"Evolutionary Policy Optimization","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WVSXG3RXX7SZR3OO5ZQGTFZSRJ","json":"https://pith.science/pith/WVSXG3RXX7SZR3OO5ZQGTFZSRJ.json","graph_json":"https://pith.science/api/pith-number/WVSXG3RXX7SZR3OO5ZQGTFZSRJ/graph.json","events_json":"https://pith.science/api/pith-number/WVSXG3RXX7SZR3OO5ZQGTFZSRJ/events.json","paper":"https://pith.science/paper/WVSXG3RX"},"agent_actions":{"view_html":"https://pith.science/pith/WVSXG3RXX7SZR3OO5ZQGTFZSRJ","download_json":"https://pith.science/pith/WVSXG3RXX7SZR3OO5ZQGTFZSRJ.json","view_paper":"https://pith.science/paper/WVSXG3RX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.05368&json=true","fetch_graph":"https://pith.science/api/pith-number/WVSXG3RXX7SZR3OO5ZQGTFZSRJ/graph.json","fetch_events":"https://pith.science/api/pith-number/WVSXG3RXX7SZR3OO5ZQGTFZSRJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WVSXG3RXX7SZR3OO5ZQGTFZSRJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WVSXG3RXX7SZR3OO5ZQGTFZSRJ/action/storage_attestation","attest_author":"https://pith.science/pith/WVSXG3RXX7SZR3OO5ZQGTFZSRJ/action/author_attestation","sign_citation":"https://pith.science/pith/WVSXG3RXX7SZR3OO5ZQGTFZSRJ/action/citation_signature","submit_replication":"https://pith.science/pith/WVSXG3RXX7SZR3OO5ZQGTFZSRJ/action/replication_record"}},"created_at":"2026-07-05T00:57:25.327939+00:00","updated_at":"2026-07-05T00:57:25.327939+00:00"}