{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NCPOCETYB6HZ3TGJ3N3SNWKDCV","short_pith_number":"pith:NCPOCETY","schema_version":"1.0","canonical_sha256":"689ee112780f8f9dccc9db7726d94315532e49c3df85ddb00d2fd3dfd0d43312","source":{"kind":"arxiv","id":"2105.00990","version":2},"attestation_state":"computed","paper":{"title":"Hierarchical Reinforcement Learning for Air-to-Air Combat","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adrian P. Pope, Daniel Javorsek, Daria Micovic, David Rosenbluth, Henry Diaz, Jaime S. Ide, Jason C. Twedt, Kevin Alcedo, Lee Ritholtz, Thayne T. Walker","submitted_at":"2021-05-03T16:40:00Z","abstract_excerpt":"Artificial Intelligence (AI) is becoming a critical component in the defense industry, as recently demonstrated by DARPA`s AlphaDogfight Trials (ADT). ADT sought to vet the feasibility of AI algorithms capable of piloting an F-16 in simulated air-to-air combat. As a participant in ADT, Lockheed Martin`s (LM) approach combines a hierarchical architecture with maximum-entropy reinforcement learning (RL), integrates expert knowledge through reward shaping, and supports modularity of policies. This approach achieved a $2^{nd}$ place finish in the final ADT event (among eight total competitors) and"},"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":"2105.00990","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-03T16:40:00Z","cross_cats_sorted":[],"title_canon_sha256":"427ddc8b2a3375d7ca7f9dfdfc8e672c9a6401d5d1f4a31b73f95668af277329","abstract_canon_sha256":"a393769db237edae6ee2c9844fede6f474a3e5204c2ff627fe0d27f0df96127e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:48:23.041600Z","signature_b64":"ziQKDU1Ip3E5sHT/+RCojNQi6bSQvDtsjrf8ZeW2/RTMn2Empj3gSUs0Xl7Pd3K/nj7XoG2HEkWg0Hqm0t5aCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"689ee112780f8f9dccc9db7726d94315532e49c3df85ddb00d2fd3dfd0d43312","last_reissued_at":"2026-07-05T02:48:23.041098Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:48:23.041098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Reinforcement Learning for Air-to-Air Combat","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adrian P. Pope, Daniel Javorsek, Daria Micovic, David Rosenbluth, Henry Diaz, Jaime S. Ide, Jason C. Twedt, Kevin Alcedo, Lee Ritholtz, Thayne T. Walker","submitted_at":"2021-05-03T16:40:00Z","abstract_excerpt":"Artificial Intelligence (AI) is becoming a critical component in the defense industry, as recently demonstrated by DARPA`s AlphaDogfight Trials (ADT). ADT sought to vet the feasibility of AI algorithms capable of piloting an F-16 in simulated air-to-air combat. As a participant in ADT, Lockheed Martin`s (LM) approach combines a hierarchical architecture with maximum-entropy reinforcement learning (RL), integrates expert knowledge through reward shaping, and supports modularity of policies. This approach achieved a $2^{nd}$ place finish in the final ADT event (among eight total competitors) and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.00990","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/2105.00990/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":"2105.00990","created_at":"2026-07-05T02:48:23.041157+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.00990v2","created_at":"2026-07-05T02:48:23.041157+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.00990","created_at":"2026-07-05T02:48:23.041157+00:00"},{"alias_kind":"pith_short_12","alias_value":"NCPOCETYB6HZ","created_at":"2026-07-05T02:48:23.041157+00:00"},{"alias_kind":"pith_short_16","alias_value":"NCPOCETYB6HZ3TGJ","created_at":"2026-07-05T02:48:23.041157+00:00"},{"alias_kind":"pith_short_8","alias_value":"NCPOCETY","created_at":"2026-07-05T02:48:23.041157+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.01953","citing_title":"Training Environment for High Performance Reinforcement Learning","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NCPOCETYB6HZ3TGJ3N3SNWKDCV","json":"https://pith.science/pith/NCPOCETYB6HZ3TGJ3N3SNWKDCV.json","graph_json":"https://pith.science/api/pith-number/NCPOCETYB6HZ3TGJ3N3SNWKDCV/graph.json","events_json":"https://pith.science/api/pith-number/NCPOCETYB6HZ3TGJ3N3SNWKDCV/events.json","paper":"https://pith.science/paper/NCPOCETY"},"agent_actions":{"view_html":"https://pith.science/pith/NCPOCETYB6HZ3TGJ3N3SNWKDCV","download_json":"https://pith.science/pith/NCPOCETYB6HZ3TGJ3N3SNWKDCV.json","view_paper":"https://pith.science/paper/NCPOCETY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.00990&json=true","fetch_graph":"https://pith.science/api/pith-number/NCPOCETYB6HZ3TGJ3N3SNWKDCV/graph.json","fetch_events":"https://pith.science/api/pith-number/NCPOCETYB6HZ3TGJ3N3SNWKDCV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NCPOCETYB6HZ3TGJ3N3SNWKDCV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NCPOCETYB6HZ3TGJ3N3SNWKDCV/action/storage_attestation","attest_author":"https://pith.science/pith/NCPOCETYB6HZ3TGJ3N3SNWKDCV/action/author_attestation","sign_citation":"https://pith.science/pith/NCPOCETYB6HZ3TGJ3N3SNWKDCV/action/citation_signature","submit_replication":"https://pith.science/pith/NCPOCETYB6HZ3TGJ3N3SNWKDCV/action/replication_record"}},"created_at":"2026-07-05T02:48:23.041157+00:00","updated_at":"2026-07-05T02:48:23.041157+00:00"}