{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SENMG2N3QPJJUZDBU3K2KLXQUT","short_pith_number":"pith:SENMG2N3","schema_version":"1.0","canonical_sha256":"911ac369bb83d29a6461a6d5a52ef0a4c929d64e06a0b4b726e957a941478254","source":{"kind":"arxiv","id":"2503.06741","version":1},"attestation_state":"computed","paper":{"title":"A Novel Multi-Objective Reinforcement Learning Algorithm for Pursuit-Evasion Game","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Chunhui Zhao, Penglin Hu, Quan Pan","submitted_at":"2025-03-09T19:49:02Z","abstract_excerpt":"In practical application, the pursuit-evasion game (PEG) often involves multiple complex and conflicting objectives. The single-objective reinforcement learning (RL) usually focuses on a single optimization objective, and it is difficult to find the optimal balance among multiple objectives. This paper proposes a three-objective RL algorithm based on fuzzy Q-learning (FQL) to solve the PEG with different optimization objectives. First, the multi-objective FQL algorithm is introduced, which uses the reward function to represent three optimization objectives: evading pursuit, reaching target, an"},"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":"2503.06741","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2025-03-09T19:49:02Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"06ec89b3e66a7304f2dc1b4c7ffafc3052c4f144f5db342982511d8808088b58","abstract_canon_sha256":"0dc8d1cbaae620d1ef376d8c346d4ea101bbd91c9e1d7328e56fc017d8cc7a7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:41.141406Z","signature_b64":"8V6WQyeJuGL0mpTWLX7tA4EViFcKSOlX6txUgXqASL8uHB18Mqh9w60tEjxYCyhtNIeonO9kl7omNM/Tu/4+Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"911ac369bb83d29a6461a6d5a52ef0a4c929d64e06a0b4b726e957a941478254","last_reissued_at":"2026-07-05T10:27:41.140458Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:41.140458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Novel Multi-Objective Reinforcement Learning Algorithm for Pursuit-Evasion Game","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Chunhui Zhao, Penglin Hu, Quan Pan","submitted_at":"2025-03-09T19:49:02Z","abstract_excerpt":"In practical application, the pursuit-evasion game (PEG) often involves multiple complex and conflicting objectives. The single-objective reinforcement learning (RL) usually focuses on a single optimization objective, and it is difficult to find the optimal balance among multiple objectives. This paper proposes a three-objective RL algorithm based on fuzzy Q-learning (FQL) to solve the PEG with different optimization objectives. First, the multi-objective FQL algorithm is introduced, which uses the reward function to represent three optimization objectives: evading pursuit, reaching target, an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06741","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/2503.06741/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":"2503.06741","created_at":"2026-07-05T10:27:41.140589+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.06741v1","created_at":"2026-07-05T10:27:41.140589+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06741","created_at":"2026-07-05T10:27:41.140589+00:00"},{"alias_kind":"pith_short_12","alias_value":"SENMG2N3QPJJ","created_at":"2026-07-05T10:27:41.140589+00:00"},{"alias_kind":"pith_short_16","alias_value":"SENMG2N3QPJJUZDB","created_at":"2026-07-05T10:27:41.140589+00:00"},{"alias_kind":"pith_short_8","alias_value":"SENMG2N3","created_at":"2026-07-05T10:27:41.140589+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/SENMG2N3QPJJUZDBU3K2KLXQUT","json":"https://pith.science/pith/SENMG2N3QPJJUZDBU3K2KLXQUT.json","graph_json":"https://pith.science/api/pith-number/SENMG2N3QPJJUZDBU3K2KLXQUT/graph.json","events_json":"https://pith.science/api/pith-number/SENMG2N3QPJJUZDBU3K2KLXQUT/events.json","paper":"https://pith.science/paper/SENMG2N3"},"agent_actions":{"view_html":"https://pith.science/pith/SENMG2N3QPJJUZDBU3K2KLXQUT","download_json":"https://pith.science/pith/SENMG2N3QPJJUZDBU3K2KLXQUT.json","view_paper":"https://pith.science/paper/SENMG2N3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.06741&json=true","fetch_graph":"https://pith.science/api/pith-number/SENMG2N3QPJJUZDBU3K2KLXQUT/graph.json","fetch_events":"https://pith.science/api/pith-number/SENMG2N3QPJJUZDBU3K2KLXQUT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SENMG2N3QPJJUZDBU3K2KLXQUT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SENMG2N3QPJJUZDBU3K2KLXQUT/action/storage_attestation","attest_author":"https://pith.science/pith/SENMG2N3QPJJUZDBU3K2KLXQUT/action/author_attestation","sign_citation":"https://pith.science/pith/SENMG2N3QPJJUZDBU3K2KLXQUT/action/citation_signature","submit_replication":"https://pith.science/pith/SENMG2N3QPJJUZDBU3K2KLXQUT/action/replication_record"}},"created_at":"2026-07-05T10:27:41.140589+00:00","updated_at":"2026-07-05T10:27:41.140589+00:00"}