{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HAWBLJ5FUJL7DUCN6RODYRHHZ4","short_pith_number":"pith:HAWBLJ5F","schema_version":"1.0","canonical_sha256":"382c15a7a5a257f1d04df45c3c44e7cf2f0e5e8af1c55354f6c257d70172efcf","source":{"kind":"arxiv","id":"2212.03830","version":1},"attestation_state":"computed","paper":{"title":"A Hierarchical Deep Reinforcement Learning Framework for 6-DOF UCAV Air-to-Air Combat","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.AI","authors_text":"Dongbin Zhao, Jiajun Chai, Wenzhang Chen, Yuanheng Zhu, Zong-xin Yao","submitted_at":"2022-12-05T07:03:25Z","abstract_excerpt":"Unmanned combat air vehicle (UCAV) combat is a challenging scenario with continuous action space. In this paper, we propose a general hierarchical framework to resolve the within-vision-range (WVR) air-to-air combat problem under 6 dimensions of degree (6-DOF) dynamics. The core idea is to divide the whole decision process into two loops and use reinforcement learning (RL) to solve them separately. The outer loop takes into account the current combat situation and decides the expected macro behavior of the aircraft according to a combat strategy. Then the inner loop tracks the macro behavior w"},"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":"2212.03830","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-12-05T07:03:25Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"e25f5aed5cc65e8547cf68f702b3ad00b4913864d3f9b1a8896aaca3aa8d874a","abstract_canon_sha256":"c34a3d0d06cb69ac3ccdbc68a1db143bf0c93adf551b0a14d4f814b94420ab3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:14.710997Z","signature_b64":"gi/dLNy8ZCu+N7stpbYOLwLoyX97MoEk6oXrXJDiNo8YwNR9GjGed3EnC2x+QjF7kwBf/+C9qI1zVcLFJLn/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"382c15a7a5a257f1d04df45c3c44e7cf2f0e5e8af1c55354f6c257d70172efcf","last_reissued_at":"2026-07-05T09:09:14.710520Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:14.710520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Hierarchical Deep Reinforcement Learning Framework for 6-DOF UCAV Air-to-Air Combat","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.AI","authors_text":"Dongbin Zhao, Jiajun Chai, Wenzhang Chen, Yuanheng Zhu, Zong-xin Yao","submitted_at":"2022-12-05T07:03:25Z","abstract_excerpt":"Unmanned combat air vehicle (UCAV) combat is a challenging scenario with continuous action space. In this paper, we propose a general hierarchical framework to resolve the within-vision-range (WVR) air-to-air combat problem under 6 dimensions of degree (6-DOF) dynamics. The core idea is to divide the whole decision process into two loops and use reinforcement learning (RL) to solve them separately. The outer loop takes into account the current combat situation and decides the expected macro behavior of the aircraft according to a combat strategy. Then the inner loop tracks the macro behavior w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.03830","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/2212.03830/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":"2212.03830","created_at":"2026-07-05T09:09:14.710574+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.03830v1","created_at":"2026-07-05T09:09:14.710574+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.03830","created_at":"2026-07-05T09:09:14.710574+00:00"},{"alias_kind":"pith_short_12","alias_value":"HAWBLJ5FUJL7","created_at":"2026-07-05T09:09:14.710574+00:00"},{"alias_kind":"pith_short_16","alias_value":"HAWBLJ5FUJL7DUCN","created_at":"2026-07-05T09:09:14.710574+00:00"},{"alias_kind":"pith_short_8","alias_value":"HAWBLJ5F","created_at":"2026-07-05T09:09:14.710574+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/HAWBLJ5FUJL7DUCN6RODYRHHZ4","json":"https://pith.science/pith/HAWBLJ5FUJL7DUCN6RODYRHHZ4.json","graph_json":"https://pith.science/api/pith-number/HAWBLJ5FUJL7DUCN6RODYRHHZ4/graph.json","events_json":"https://pith.science/api/pith-number/HAWBLJ5FUJL7DUCN6RODYRHHZ4/events.json","paper":"https://pith.science/paper/HAWBLJ5F"},"agent_actions":{"view_html":"https://pith.science/pith/HAWBLJ5FUJL7DUCN6RODYRHHZ4","download_json":"https://pith.science/pith/HAWBLJ5FUJL7DUCN6RODYRHHZ4.json","view_paper":"https://pith.science/paper/HAWBLJ5F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.03830&json=true","fetch_graph":"https://pith.science/api/pith-number/HAWBLJ5FUJL7DUCN6RODYRHHZ4/graph.json","fetch_events":"https://pith.science/api/pith-number/HAWBLJ5FUJL7DUCN6RODYRHHZ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HAWBLJ5FUJL7DUCN6RODYRHHZ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HAWBLJ5FUJL7DUCN6RODYRHHZ4/action/storage_attestation","attest_author":"https://pith.science/pith/HAWBLJ5FUJL7DUCN6RODYRHHZ4/action/author_attestation","sign_citation":"https://pith.science/pith/HAWBLJ5FUJL7DUCN6RODYRHHZ4/action/citation_signature","submit_replication":"https://pith.science/pith/HAWBLJ5FUJL7DUCN6RODYRHHZ4/action/replication_record"}},"created_at":"2026-07-05T09:09:14.710574+00:00","updated_at":"2026-07-05T09:09:14.710574+00:00"}