{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:U2AHWU3UHZDAG3L4AOB5PC6XS6","short_pith_number":"pith:U2AHWU3U","schema_version":"1.0","canonical_sha256":"a6807b53743e46036d7c0383d78bd797add0522d09c344ebd0cb4bae935e0374","source":{"kind":"arxiv","id":"2507.00762","version":2},"attestation_state":"computed","paper":{"title":"Leveraging Genetic Algorithms for Efficient Demonstration Generation in Real-World Reinforcement Learning Environments","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Asma Atamna, Tobias Glasmachers, Tom Maus","submitted_at":"2025-07-01T14:04:17Z","abstract_excerpt":"Reinforcement Learning (RL) has demonstrated significant potential in certain real-world industrial applications, yet its broader deployment remains limited by inherent challenges such as sample inefficiency and unstable learning dynamics. This study investigates the utilization of Genetic Algorithms (GAs) as a mechanism for improving RL performance in an industrially inspired sorting environment. We propose a novel approach in which GA-generated expert demonstrations are used to enhance policy learning. These demonstrations are incorporated into a Deep Q-Network (DQN) replay buffer for experi"},"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":"2507.00762","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-01T14:04:17Z","cross_cats_sorted":[],"title_canon_sha256":"90c8b11f9cc3adbbfb5abc3e197fbac3af3075c2c7359fcba9f00d99b47e8e8f","abstract_canon_sha256":"b6b0de3e5fd13af16250b83121199a6a788cb19244c8befb06f52119a1c6c6bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:46.165478Z","signature_b64":"XqOpt1mw+2xm4yph9DnRSKYUPMwaqoloV6grijRJxr7eQ0nhVD4Wnoy2j7UM4nTexdXqoiHDYwK+N+/qasmEBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6807b53743e46036d7c0383d78bd797add0522d09c344ebd0cb4bae935e0374","last_reissued_at":"2026-07-05T11:30:46.164961Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:46.164961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Genetic Algorithms for Efficient Demonstration Generation in Real-World Reinforcement Learning Environments","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Asma Atamna, Tobias Glasmachers, Tom Maus","submitted_at":"2025-07-01T14:04:17Z","abstract_excerpt":"Reinforcement Learning (RL) has demonstrated significant potential in certain real-world industrial applications, yet its broader deployment remains limited by inherent challenges such as sample inefficiency and unstable learning dynamics. This study investigates the utilization of Genetic Algorithms (GAs) as a mechanism for improving RL performance in an industrially inspired sorting environment. We propose a novel approach in which GA-generated expert demonstrations are used to enhance policy learning. These demonstrations are incorporated into a Deep Q-Network (DQN) replay buffer for experi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00762","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/2507.00762/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":"2507.00762","created_at":"2026-07-05T11:30:46.165025+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.00762v2","created_at":"2026-07-05T11:30:46.165025+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00762","created_at":"2026-07-05T11:30:46.165025+00:00"},{"alias_kind":"pith_short_12","alias_value":"U2AHWU3UHZDA","created_at":"2026-07-05T11:30:46.165025+00:00"},{"alias_kind":"pith_short_16","alias_value":"U2AHWU3UHZDAG3L4","created_at":"2026-07-05T11:30:46.165025+00:00"},{"alias_kind":"pith_short_8","alias_value":"U2AHWU3U","created_at":"2026-07-05T11:30:46.165025+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/U2AHWU3UHZDAG3L4AOB5PC6XS6","json":"https://pith.science/pith/U2AHWU3UHZDAG3L4AOB5PC6XS6.json","graph_json":"https://pith.science/api/pith-number/U2AHWU3UHZDAG3L4AOB5PC6XS6/graph.json","events_json":"https://pith.science/api/pith-number/U2AHWU3UHZDAG3L4AOB5PC6XS6/events.json","paper":"https://pith.science/paper/U2AHWU3U"},"agent_actions":{"view_html":"https://pith.science/pith/U2AHWU3UHZDAG3L4AOB5PC6XS6","download_json":"https://pith.science/pith/U2AHWU3UHZDAG3L4AOB5PC6XS6.json","view_paper":"https://pith.science/paper/U2AHWU3U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.00762&json=true","fetch_graph":"https://pith.science/api/pith-number/U2AHWU3UHZDAG3L4AOB5PC6XS6/graph.json","fetch_events":"https://pith.science/api/pith-number/U2AHWU3UHZDAG3L4AOB5PC6XS6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U2AHWU3UHZDAG3L4AOB5PC6XS6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U2AHWU3UHZDAG3L4AOB5PC6XS6/action/storage_attestation","attest_author":"https://pith.science/pith/U2AHWU3UHZDAG3L4AOB5PC6XS6/action/author_attestation","sign_citation":"https://pith.science/pith/U2AHWU3UHZDAG3L4AOB5PC6XS6/action/citation_signature","submit_replication":"https://pith.science/pith/U2AHWU3UHZDAG3L4AOB5PC6XS6/action/replication_record"}},"created_at":"2026-07-05T11:30:46.165025+00:00","updated_at":"2026-07-05T11:30:46.165025+00:00"}