{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:BEX2FOIS37BX2PZJ2PH4CVF5YB","short_pith_number":"pith:BEX2FOIS","schema_version":"1.0","canonical_sha256":"092fa2b912dfc37d3f29d3cfc154bdc06693394d5f599505a34f8b8cf01c2170","source":{"kind":"arxiv","id":"1805.07917","version":2},"attestation_state":"computed","paper":{"title":"Evolution-Guided Policy Gradient in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kagan Tumer, Shauharda Khadka","submitted_at":"2018-05-21T06:55:58Z","abstract_excerpt":"Deep Reinforcement Learning (DRL) algorithms have been successfully applied to a range of challenging control tasks. However, these methods typically suffer from three core difficulties: temporal credit assignment with sparse rewards, lack of effective exploration, and brittle convergence properties that are extremely sensitive to hyperparameters. Collectively, these challenges severely limit the applicability of these approaches to real-world problems. Evolutionary Algorithms (EAs), a class of black box optimization techniques inspired by natural evolution, are well suited to address each of "},"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":"1805.07917","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-21T06:55:58Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"2b75a128427869edb026f997d655f6f02762230b1950bb491b8693a2217223c8","abstract_canon_sha256":"b18fd1425e43afc6014d996856da7f085121fba0ef8c14303843d71575626d1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:09.998352Z","signature_b64":"2FK9y5lvBbpEjXlnJojiC03aFCxlexv0suALBd4DrwhdcCfTEW5uXIiUjP0E5jDMmiHVUuPBN9ayKyHxzEoyDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"092fa2b912dfc37d3f29d3cfc154bdc06693394d5f599505a34f8b8cf01c2170","last_reissued_at":"2026-05-18T00:02:09.997667Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:09.997667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evolution-Guided Policy Gradient in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kagan Tumer, Shauharda Khadka","submitted_at":"2018-05-21T06:55:58Z","abstract_excerpt":"Deep Reinforcement Learning (DRL) algorithms have been successfully applied to a range of challenging control tasks. However, these methods typically suffer from three core difficulties: temporal credit assignment with sparse rewards, lack of effective exploration, and brittle convergence properties that are extremely sensitive to hyperparameters. Collectively, these challenges severely limit the applicability of these approaches to real-world problems. Evolutionary Algorithms (EAs), a class of black box optimization techniques inspired by natural evolution, are well suited to address each of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07917","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":"1805.07917","created_at":"2026-05-18T00:02:09.997779+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.07917v2","created_at":"2026-05-18T00:02:09.997779+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07917","created_at":"2026-05-18T00:02:09.997779+00:00"},{"alias_kind":"pith_short_12","alias_value":"BEX2FOIS37BX","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_16","alias_value":"BEX2FOIS37BX2PZJ","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_8","alias_value":"BEX2FOIS","created_at":"2026-05-18T12:32:16.446611+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/BEX2FOIS37BX2PZJ2PH4CVF5YB","json":"https://pith.science/pith/BEX2FOIS37BX2PZJ2PH4CVF5YB.json","graph_json":"https://pith.science/api/pith-number/BEX2FOIS37BX2PZJ2PH4CVF5YB/graph.json","events_json":"https://pith.science/api/pith-number/BEX2FOIS37BX2PZJ2PH4CVF5YB/events.json","paper":"https://pith.science/paper/BEX2FOIS"},"agent_actions":{"view_html":"https://pith.science/pith/BEX2FOIS37BX2PZJ2PH4CVF5YB","download_json":"https://pith.science/pith/BEX2FOIS37BX2PZJ2PH4CVF5YB.json","view_paper":"https://pith.science/paper/BEX2FOIS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.07917&json=true","fetch_graph":"https://pith.science/api/pith-number/BEX2FOIS37BX2PZJ2PH4CVF5YB/graph.json","fetch_events":"https://pith.science/api/pith-number/BEX2FOIS37BX2PZJ2PH4CVF5YB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BEX2FOIS37BX2PZJ2PH4CVF5YB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BEX2FOIS37BX2PZJ2PH4CVF5YB/action/storage_attestation","attest_author":"https://pith.science/pith/BEX2FOIS37BX2PZJ2PH4CVF5YB/action/author_attestation","sign_citation":"https://pith.science/pith/BEX2FOIS37BX2PZJ2PH4CVF5YB/action/citation_signature","submit_replication":"https://pith.science/pith/BEX2FOIS37BX2PZJ2PH4CVF5YB/action/replication_record"}},"created_at":"2026-05-18T00:02:09.997779+00:00","updated_at":"2026-05-18T00:02:09.997779+00:00"}