{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:D4476L54SXSKWF3OM5D5XHOL2Z","short_pith_number":"pith:D4476L54","schema_version":"1.0","canonical_sha256":"1f39ff2fbc95e4ab176e6747db9dcbd655e571f59b83bd631fdcc891d18cdcd0","source":{"kind":"arxiv","id":"2410.21940","version":1},"attestation_state":"computed","paper":{"title":"Human-Readable Programs as Actors of Reinforcement Learning Agents Using Critic-Moderated Evolution","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ann Now\\'e, Denis Steckelmacher, Senne Deproost","submitted_at":"2024-10-29T10:57:33Z","abstract_excerpt":"With Deep Reinforcement Learning (DRL) being increasingly considered for the control of real-world systems, the lack of transparency of the neural network at the core of RL becomes a concern. Programmatic Reinforcement Learning (PRL) is able to to create representations of this black-box in the form of source code, not only increasing the explainability of the controller but also allowing for user adaptations. However, these methods focus on distilling a black-box policy into a program and do so after learning using the Mean Squared Error between produced and wanted behaviour, discarding other"},"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":"2410.21940","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-29T10:57:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a27af972fecc94c076b6a1a4feac9ad49f3d0a4eb480e8ed88558490688faa23","abstract_canon_sha256":"b794ae78d32ef12a0889ba1e9a589c912b5e2b3e573b53a57166abe8bb443a96"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:01.999893Z","signature_b64":"Hmhg+scVTzjeIZ9LaNq0ZCIL+CE8hJ4ge/wVHEG1Kie4a/6+qloZmeOq2FRON/TxU2XZUsMvUGceUffI+tBGCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f39ff2fbc95e4ab176e6747db9dcbd655e571f59b83bd631fdcc891d18cdcd0","last_reissued_at":"2026-07-05T09:28:01.999486Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:01.999486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Human-Readable Programs as Actors of Reinforcement Learning Agents Using Critic-Moderated Evolution","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ann Now\\'e, Denis Steckelmacher, Senne Deproost","submitted_at":"2024-10-29T10:57:33Z","abstract_excerpt":"With Deep Reinforcement Learning (DRL) being increasingly considered for the control of real-world systems, the lack of transparency of the neural network at the core of RL becomes a concern. Programmatic Reinforcement Learning (PRL) is able to to create representations of this black-box in the form of source code, not only increasing the explainability of the controller but also allowing for user adaptations. However, these methods focus on distilling a black-box policy into a program and do so after learning using the Mean Squared Error between produced and wanted behaviour, discarding other"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21940","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/2410.21940/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":"2410.21940","created_at":"2026-07-05T09:28:01.999545+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.21940v1","created_at":"2026-07-05T09:28:01.999545+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21940","created_at":"2026-07-05T09:28:01.999545+00:00"},{"alias_kind":"pith_short_12","alias_value":"D4476L54SXSK","created_at":"2026-07-05T09:28:01.999545+00:00"},{"alias_kind":"pith_short_16","alias_value":"D4476L54SXSKWF3O","created_at":"2026-07-05T09:28:01.999545+00:00"},{"alias_kind":"pith_short_8","alias_value":"D4476L54","created_at":"2026-07-05T09:28:01.999545+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.04254","citing_title":"Hierarchical Support Vector State Partitioning for Distilling Black Box Reinforcement Learning Policies","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04254","citing_title":"Hierarchical Support Vector State Partitioning for Distilling Black Box Reinforcement Learning Policies","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04254","citing_title":"Hierarchical Support Vector State Partitioning for Distilling Black Box Reinforcement Learning Policies","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D4476L54SXSKWF3OM5D5XHOL2Z","json":"https://pith.science/pith/D4476L54SXSKWF3OM5D5XHOL2Z.json","graph_json":"https://pith.science/api/pith-number/D4476L54SXSKWF3OM5D5XHOL2Z/graph.json","events_json":"https://pith.science/api/pith-number/D4476L54SXSKWF3OM5D5XHOL2Z/events.json","paper":"https://pith.science/paper/D4476L54"},"agent_actions":{"view_html":"https://pith.science/pith/D4476L54SXSKWF3OM5D5XHOL2Z","download_json":"https://pith.science/pith/D4476L54SXSKWF3OM5D5XHOL2Z.json","view_paper":"https://pith.science/paper/D4476L54","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.21940&json=true","fetch_graph":"https://pith.science/api/pith-number/D4476L54SXSKWF3OM5D5XHOL2Z/graph.json","fetch_events":"https://pith.science/api/pith-number/D4476L54SXSKWF3OM5D5XHOL2Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D4476L54SXSKWF3OM5D5XHOL2Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D4476L54SXSKWF3OM5D5XHOL2Z/action/storage_attestation","attest_author":"https://pith.science/pith/D4476L54SXSKWF3OM5D5XHOL2Z/action/author_attestation","sign_citation":"https://pith.science/pith/D4476L54SXSKWF3OM5D5XHOL2Z/action/citation_signature","submit_replication":"https://pith.science/pith/D4476L54SXSKWF3OM5D5XHOL2Z/action/replication_record"}},"created_at":"2026-07-05T09:28:01.999545+00:00","updated_at":"2026-07-05T09:28:01.999545+00:00"}