{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T15:54:48Z","timestamp":1783612488637,"version":"3.55.0"},"reference-count":69,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1109\/tai.2022.3222143","type":"journal-article","created":{"date-parts":[[2022,11,15]],"date-time":"2022-11-15T15:43:21Z","timestamp":1668527001000},"page":"1371-1385","source":"Crossref","is-referenced-by-count":85,"title":["Hierarchical Reinforcement Learning for Air Combat at DARPA's AlphaDogfight Trials"],"prefix":"10.1109","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2723-0581","authenticated-orcid":false,"given":"Adrian P.","family":"Pope","sequence":"first","affiliation":[{"name":"Lockheed Martin Artificial Intelligence Center, Applied AI Team, Shelton, CT, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7223-1102","authenticated-orcid":false,"given":"Jaime S.","family":"Ide","sequence":"additional","affiliation":[{"name":"Lockheed Martin Artificial Intelligence Center, Applied AI Team, Shelton, CT, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daria","family":"Mi\u0107ovi\u0107","sequence":"additional","affiliation":[{"name":"Lockheed Martin Artificial Intelligence Center, Applied AI Team, Shelton, CT, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Henry","family":"Diaz","sequence":"additional","affiliation":[{"name":"Lockheed Martin Artificial Intelligence Center, Applied AI Team, Shelton, CT, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jason C.","family":"Twedt","sequence":"additional","affiliation":[{"name":"Lockheed Martin Artificial Intelligence Center, Applied AI Team, Shelton, CT, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kevin","family":"Alcedo","sequence":"additional","affiliation":[{"name":"Lockheed Martin Artificial Intelligence Center, Applied AI Team, Shelton, CT, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thayne T.","family":"Walker","sequence":"additional","affiliation":[{"name":"Lockheed Martin Artificial Intelligence Center, Applied AI Team, Shelton, CT, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Rosenbluth","sequence":"additional","affiliation":[{"name":"Lockheed Martin Artificial Intelligence Center, Applied AI Team, Shelton, CT, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lee","family":"Ritholtz","sequence":"additional","affiliation":[{"name":"Lockheed Martin Artificial Intelligence Center, Applied AI Team, Shelton, CT, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0329-4011","authenticated-orcid":false,"given":"Daniel","family":"Javorsek","sequence":"additional","affiliation":[{"name":"United States Air Force, Nellis Air Force Base, Las Vegas, NV, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2961426"},{"key":"ref57","article-title":"Categorical reparameterization with Gumbel-Softmax","author":"jang","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IAEAC47372.2019.8998066"},{"key":"ref56","article-title":"Soft actor-critic for discrete action settings","author":"christodoulou","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/7180639"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1017\/S026988890500041X"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.3390\/electronics9071121","article-title":"UAV autonomous aerial combat maneuver strategy generation with observation error based on state-adversarial deep deterministic policy gradient and inverse reinforcement learning","volume":"9","author":"kong","year":"2020","journal-title":"Electronics"},{"key":"ref58","article-title":"Distributed prioritized experience replay","author":"horgan","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref53","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"0","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.2514\/6.2004-4923"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICARCV50220.2020.9305467"},{"key":"ref55","article-title":"Flight training instruction for basic fighter maneuvering (BFM) advanced strike\/fighter NFO training system","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.7249\/RR4311"},{"key":"ref54","article-title":"Training larger networks for deep reinforcement learning","author":"ota","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.23919\/ICCAS52745.2021.9649876"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICUAS51884.2021.9476700"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11831-015-9147-y"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2020.104112"},{"key":"ref51","first-page":"130","article-title":"Learning to generalize from sparse and underspecified rewards","author":"agarwal","year":"0","journal-title":"Proc 36th Int Conf Mach Learn"},{"key":"ref50","article-title":"Hindsight policy gradients","author":"rauber","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref45","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref48","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","author":"ng","year":"0","journal-title":"Proc 16th Int Conf Mach Learn"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50030-1"},{"key":"ref42","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref41","article-title":"Modeling purposeful adaptive behavior with the principle of maximum causal entropy","author":"ziebart","year":"2010"},{"key":"ref44","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"0","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref43","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"0","journal-title":"Proc 4th Int Conf Learn Representations"},{"key":"ref49","article-title":"Hindsight experience replay","volume":"30","author":"andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.2514\/6.1989-3525"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.2514\/3.20590"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.4172\/2167-0374.1000144"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.2514\/1.46815"},{"key":"ref3","article-title":"Rule-based air combat simulation","author":"burgin","year":"1988"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.2514\/1.17168"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/0898-1221(92)90217-6"},{"key":"ref40","first-page":"1861","article-title":"Soft actor-critic algorithms and applications","volume":"80","author":"haarnoja","year":"0","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref35","first-page":"10510","article-title":"Diversity-driven exploration strategy for deep reinforcement learning","author":"hong","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref34","author":"mitchell","year":"1997","journal-title":"Machine Learning"},{"key":"ref37","article-title":"Equivalence between policy gradients and soft Q-learning","author":"schulman","year":"2017"},{"key":"ref36","first-page":"441","article-title":"Bias in natural actor-critic algorithms","author":"thomas","year":"0","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref31","article-title":"The promise of hierarchical reinforcement learning","author":"flet-berliac","year":"2019","journal-title":"GradientSHAP"},{"key":"ref30","first-page":"3303","article-title":"Data-efficient hierarchical reinforcement learning","author":"nachum","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref33","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref32","article-title":"Meta learning shared hierarchies","author":"frans","year":"0","journal-title":"Proc 6th Int Conf Learn Representations"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v24i1.7576"},{"key":"ref1","article-title":"Games of pursuit","author":"isaacs","year":"1951"},{"key":"ref39","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"0","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref38","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","author":"haarnoja","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref68","doi-asserted-by":"crossref","DOI":"10.3390\/electronics10121491","article-title":"Virtual to real-world transfer learning: A systematic review","volume":"10","author":"ranaweera","year":"2021","journal-title":"Electronics"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1991.155375"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05982-z"},{"key":"ref26","first-page":"709","article-title":"Optimal policy switching algorithms for reinforcement learning","author":"comanici","year":"0","journal-title":"Proc 9th Int Conf Auton Agents Multiagent Syst"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.conb.2012.05.008"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.2201-12.2013"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.5772\/120"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1177\/0278364918770733"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022140919877"},{"key":"ref66","first-page":"110","article-title":"Multi-agent manipulation via locomotion using hierarchical sim2real","volume":"100","author":"nachum","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref21","first-page":"271","article-title":"Feudal reinforcement learning","author":"dayan","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref27","first-page":"1312","article-title":"Universal value function approximators","author":"schaul","year":"0","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref29","first-page":"3540","article-title":"Feudal networks for hierarchical reinforcement learning","author":"vezhnevets","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref60","first-page":"1501","article-title":"Pick your battles: Interaction graphs as population-level objectives for strategic diversity","author":"garnelo","year":"0","journal-title":"Proc Auton Agents Multiagent Syst"},{"key":"ref62","article-title":"Composing complex skills by learning transition policies","author":"lee","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref61","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9078688\/10330793\/09950612.pdf?arnumber=9950612","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T18:02:15Z","timestamp":1761242535000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9950612\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":69,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tai.2022.3222143","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12]]}}}