{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RP3GXLKZYWCOT4IB3SY34MSP4P","short_pith_number":"pith:RP3GXLKZ","schema_version":"1.0","canonical_sha256":"8bf66bad59c584e9f101dcb1be324fe3e59f89acbae9087518ef917bbeb4b878","source":{"kind":"arxiv","id":"2301.13374","version":1},"attestation_state":"computed","paper":{"title":"Enabling surrogate-assisted evolutionary reinforcement learning via policy embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Guiying Li, Jinyuan Zhang, Ke Tang, Lan Tang, Peng Yang, Xiaxi Li","submitted_at":"2023-01-31T02:36:06Z","abstract_excerpt":"Evolutionary Reinforcement Learning (ERL) that applying Evolutionary Algorithms (EAs) to optimize the weight parameters of Deep Neural Network (DNN) based policies has been widely regarded as an alternative to traditional reinforcement learning methods. However, the evaluation of the iteratively generated population usually requires a large amount of computational time and can be prohibitively expensive, which may potentially restrict the applicability of ERL. Surrogate is often used to reduce the computational burden of evaluation in EAs. Unfortunately, in ERL, each individual of policy usual"},"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":"2301.13374","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2023-01-31T02:36:06Z","cross_cats_sorted":[],"title_canon_sha256":"9d2d6d173cdc62942380806ac31f7fd868892569475d1e7f491946120f5dd304","abstract_canon_sha256":"3566a14071755f7bc2487660827b8fd5e5f6ed2eab41b9eb2edba946e4e1639b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:37:14.054721Z","signature_b64":"qrzMkHzj9/JUxfGLCFp3J+1nUcARkCp1apZH4nZnnBG8peOOsMrpWaaS5I5NBb1bYAcfcRsxWtLfyA7HtLZ+AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bf66bad59c584e9f101dcb1be324fe3e59f89acbae9087518ef917bbeb4b878","last_reissued_at":"2026-07-05T05:37:14.054276Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:37:14.054276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enabling surrogate-assisted evolutionary reinforcement learning via policy embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Guiying Li, Jinyuan Zhang, Ke Tang, Lan Tang, Peng Yang, Xiaxi Li","submitted_at":"2023-01-31T02:36:06Z","abstract_excerpt":"Evolutionary Reinforcement Learning (ERL) that applying Evolutionary Algorithms (EAs) to optimize the weight parameters of Deep Neural Network (DNN) based policies has been widely regarded as an alternative to traditional reinforcement learning methods. However, the evaluation of the iteratively generated population usually requires a large amount of computational time and can be prohibitively expensive, which may potentially restrict the applicability of ERL. Surrogate is often used to reduce the computational burden of evaluation in EAs. Unfortunately, in ERL, each individual of policy usual"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13374","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/2301.13374/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":"2301.13374","created_at":"2026-07-05T05:37:14.054338+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.13374v1","created_at":"2026-07-05T05:37:14.054338+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13374","created_at":"2026-07-05T05:37:14.054338+00:00"},{"alias_kind":"pith_short_12","alias_value":"RP3GXLKZYWCO","created_at":"2026-07-05T05:37:14.054338+00:00"},{"alias_kind":"pith_short_16","alias_value":"RP3GXLKZYWCOT4IB","created_at":"2026-07-05T05:37:14.054338+00:00"},{"alias_kind":"pith_short_8","alias_value":"RP3GXLKZ","created_at":"2026-07-05T05:37:14.054338+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/RP3GXLKZYWCOT4IB3SY34MSP4P","json":"https://pith.science/pith/RP3GXLKZYWCOT4IB3SY34MSP4P.json","graph_json":"https://pith.science/api/pith-number/RP3GXLKZYWCOT4IB3SY34MSP4P/graph.json","events_json":"https://pith.science/api/pith-number/RP3GXLKZYWCOT4IB3SY34MSP4P/events.json","paper":"https://pith.science/paper/RP3GXLKZ"},"agent_actions":{"view_html":"https://pith.science/pith/RP3GXLKZYWCOT4IB3SY34MSP4P","download_json":"https://pith.science/pith/RP3GXLKZYWCOT4IB3SY34MSP4P.json","view_paper":"https://pith.science/paper/RP3GXLKZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.13374&json=true","fetch_graph":"https://pith.science/api/pith-number/RP3GXLKZYWCOT4IB3SY34MSP4P/graph.json","fetch_events":"https://pith.science/api/pith-number/RP3GXLKZYWCOT4IB3SY34MSP4P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RP3GXLKZYWCOT4IB3SY34MSP4P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RP3GXLKZYWCOT4IB3SY34MSP4P/action/storage_attestation","attest_author":"https://pith.science/pith/RP3GXLKZYWCOT4IB3SY34MSP4P/action/author_attestation","sign_citation":"https://pith.science/pith/RP3GXLKZYWCOT4IB3SY34MSP4P/action/citation_signature","submit_replication":"https://pith.science/pith/RP3GXLKZYWCOT4IB3SY34MSP4P/action/replication_record"}},"created_at":"2026-07-05T05:37:14.054338+00:00","updated_at":"2026-07-05T05:37:14.054338+00:00"}