{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AEYQM4ZDC57XRMJ44W3N3ZSYGO","short_pith_number":"pith:AEYQM4ZD","schema_version":"1.0","canonical_sha256":"0131067323177f78b13ce5b6dde65833bd320364666bd7e4a8af5f728f94cbb3","source":{"kind":"arxiv","id":"2304.03489","version":1},"attestation_state":"computed","paper":{"title":"Deep Reinforcement Learning Based Optimal Infinite-Horizon Control of Probabilistic Boolean Control Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Fangfei Li, Jingjie Ni, Zheng-Guang Wu","submitted_at":"2023-04-07T06:09:20Z","abstract_excerpt":"In this paper, a deep reinforcement learning based method is proposed to obtain optimal policies for optimal infinite-horizon control of probabilistic Boolean control networks (PBCNs). Compared with the existing literatures, the proposed method is model-free, namely, the system model and the initial states needn't to be known. Meanwhile, it is suitable for large-scale PBCNs. First, we establish the connection between deep reinforcement learning and optimal infinite-horizon control, and structure the problem into the framework of the Markov decision process. Then, PBCNs are defined as large-sca"},"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":"2304.03489","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2023-04-07T06:09:20Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"73cb6ef864b1a58cddcf3d645bfffaaff0e3d120eef695625480b09c40803de1","abstract_canon_sha256":"4c81ae4a74cde7f193aea2340a4e50ef50a524d73fc4e80ffc945cb4a488b9a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:58:56.442683Z","signature_b64":"5jlGgsBSHyTH33HGfMUT+cWAG9fNcwwuRxqwZsSLE0pu26ehPOh6u/KEEdk6qrNGfaTk1Tz+KG/VB0fqpQXKCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0131067323177f78b13ce5b6dde65833bd320364666bd7e4a8af5f728f94cbb3","last_reissued_at":"2026-07-05T05:58:56.442274Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:58:56.442274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning Based Optimal Infinite-Horizon Control of Probabilistic Boolean Control Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Fangfei Li, Jingjie Ni, Zheng-Guang Wu","submitted_at":"2023-04-07T06:09:20Z","abstract_excerpt":"In this paper, a deep reinforcement learning based method is proposed to obtain optimal policies for optimal infinite-horizon control of probabilistic Boolean control networks (PBCNs). Compared with the existing literatures, the proposed method is model-free, namely, the system model and the initial states needn't to be known. Meanwhile, it is suitable for large-scale PBCNs. First, we establish the connection between deep reinforcement learning and optimal infinite-horizon control, and structure the problem into the framework of the Markov decision process. Then, PBCNs are defined as large-sca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.03489","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/2304.03489/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":"2304.03489","created_at":"2026-07-05T05:58:56.442338+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.03489v1","created_at":"2026-07-05T05:58:56.442338+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03489","created_at":"2026-07-05T05:58:56.442338+00:00"},{"alias_kind":"pith_short_12","alias_value":"AEYQM4ZDC57X","created_at":"2026-07-05T05:58:56.442338+00:00"},{"alias_kind":"pith_short_16","alias_value":"AEYQM4ZDC57XRMJ4","created_at":"2026-07-05T05:58:56.442338+00:00"},{"alias_kind":"pith_short_8","alias_value":"AEYQM4ZD","created_at":"2026-07-05T05:58:56.442338+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/AEYQM4ZDC57XRMJ44W3N3ZSYGO","json":"https://pith.science/pith/AEYQM4ZDC57XRMJ44W3N3ZSYGO.json","graph_json":"https://pith.science/api/pith-number/AEYQM4ZDC57XRMJ44W3N3ZSYGO/graph.json","events_json":"https://pith.science/api/pith-number/AEYQM4ZDC57XRMJ44W3N3ZSYGO/events.json","paper":"https://pith.science/paper/AEYQM4ZD"},"agent_actions":{"view_html":"https://pith.science/pith/AEYQM4ZDC57XRMJ44W3N3ZSYGO","download_json":"https://pith.science/pith/AEYQM4ZDC57XRMJ44W3N3ZSYGO.json","view_paper":"https://pith.science/paper/AEYQM4ZD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.03489&json=true","fetch_graph":"https://pith.science/api/pith-number/AEYQM4ZDC57XRMJ44W3N3ZSYGO/graph.json","fetch_events":"https://pith.science/api/pith-number/AEYQM4ZDC57XRMJ44W3N3ZSYGO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AEYQM4ZDC57XRMJ44W3N3ZSYGO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AEYQM4ZDC57XRMJ44W3N3ZSYGO/action/storage_attestation","attest_author":"https://pith.science/pith/AEYQM4ZDC57XRMJ44W3N3ZSYGO/action/author_attestation","sign_citation":"https://pith.science/pith/AEYQM4ZDC57XRMJ44W3N3ZSYGO/action/citation_signature","submit_replication":"https://pith.science/pith/AEYQM4ZDC57XRMJ44W3N3ZSYGO/action/replication_record"}},"created_at":"2026-07-05T05:58:56.442338+00:00","updated_at":"2026-07-05T05:58:56.442338+00:00"}