{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T14:11:11Z","timestamp":1758636671537,"version":"3.28.0"},"reference-count":126,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,23]],"date-time":"2024-04-23T00:00:00Z","timestamp":1713830400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,23]],"date-time":"2024-04-23T00:00:00Z","timestamp":1713830400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,23]]},"DOI":"10.1109\/icmcis61231.2024.10540933","type":"proceedings-article","created":{"date-parts":[[2024,6,5]],"date-time":"2024-06-05T17:39:35Z","timestamp":1717609175000},"page":"1-10","source":"Crossref","is-referenced-by-count":3,"title":["Scalable Interactive Machine Learning for Future Command and Control"],"prefix":"10.1109","author":[{"given":"Anna","family":"Madison","sequence":"first","affiliation":[{"name":"Humans in Complex Systems, U.S. DEVCOM Army Research Laboratory,Aberdeen Proving Ground,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ellen","family":"Novoseller","sequence":"additional","affiliation":[{"name":"Humans in Complex Systems, U.S. DEVCOM Army Research Laboratory,Aberdeen Proving Ground,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vinicius G.","family":"Goecks","sequence":"additional","affiliation":[{"name":"Humans in Complex Systems, U.S. DEVCOM Army Research Laboratory,Aberdeen Proving Ground,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Benjamin T.","family":"Files","sequence":"additional","affiliation":[{"name":"Humans in Complex Systems, U.S. DEVCOM Army Research Laboratory,Aberdeen Proving Ground,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicholas","family":"Waytowich","sequence":"additional","affiliation":[{"name":"Humans in Complex Systems, U.S. DEVCOM Army Research Laboratory,Aberdeen Proving Ground,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alfred","family":"Yu","sequence":"additional","affiliation":[{"name":"Humans in Complex Systems, U.S. DEVCOM Army Research Laboratory,Aberdeen Proving Ground,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vernon J.","family":"Lawhern","sequence":"additional","affiliation":[{"name":"Humans in Complex Systems, U.S. DEVCOM Army Research Laboratory,Aberdeen Proving Ground,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Steven","family":"Thurman","sequence":"additional","affiliation":[{"name":"Humans in Complex Systems, U.S. DEVCOM Army Research Laboratory,Aberdeen Proving Ground,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christopher","family":"Kelshaw","sequence":"additional","affiliation":[{"name":"U.S. Mission Command Battle Lab, Futures Branch,Ft. Leavenworth,KS,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaleb","family":"McDowell","sequence":"additional","affiliation":[{"name":"Humans in Complex Systems, U.S. DEVCOM Army Research Laboratory,Aberdeen Proving Ground,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Army Field Manual 6\u20130: Commander and Staff Organization and Operations","article-title":"Headquarters, Department of the Army","year":"2022","key":"ref1"},{"journal-title":"Army Doctrine Publication 6\u20130, Mission Command: Command and Control of Army Forces","article-title":"Headquarters, Department of the Army","year":"2019","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21428\/61b2215c"},{"key":"ref4","first-page":"151","article-title":"Centaur warfighting: The false choice of humans vs. automation","volume":"30","author":"Scharre","year":"2016","journal-title":"Temp. Intl & Comp. LJ"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/884"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3078298"},{"journal-title":"Army Doctrine Publication 5\u20130: The Operations Process","article-title":"Headquarters, Department of the Army","year":"2019","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICMCIS61231.2024.10540901"},{"key":"ref9","first-page":"64","article-title":"Four-dimensional planning at the speed of relevance: Artificial-intelligence-enabled military decision-making process","author":"Farmer","year":"2022","journal-title":"Military Review"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1177\/15485129221115736"},{"key":"ref11","article-title":"Introducing ChatGPT","volume-title":"Internet","author":"Blog","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33012462"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.065"},{"article-title":"DisasterResponseGPT: Large language models for accelerated plan of action development in disaster response scenarios","volume-title":"Workshop on Challenges in Deployable Generative AI at International Conference on Machine Learning","author":"Goecks","key":"ref15"},{"key":"ref16","article-title":"Deep reinforcement learning from human preferences","author":"Christiano","year":"2017","journal-title":"Advances in neural information processing systems"},{"article-title":"PEBBLE: Feedback-efficient interactive reinforcement learning via relabeling experience and unsupervised pre-training","volume-title":"International Conference on Machine Learning","author":"Lee","key":"ref17"},{"key":"ref18","article-title":"Learning to summarize with human feedback","author":"Stiennon","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1049\/el.2019.0244"},{"article-title":"Model-based multiagent policy optimization with adaptive opponent-wise rollouts","volume-title":"International Joint Conference on Artificial Intelligence","author":"Zhang","key":"ref20"},{"article-title":"Model-based reinforcement learning for decentralized multiagent rendezvous","volume-title":"Conference on Robot Learning","author":"Wang","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2021.3097290"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1111\/tops.12525"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1126\/science.ade9097"},{"article-title":"Coordinated multi-agent imitation learning","volume-title":"International Conference on Machine Learning","author":"Le","key":"ref26"},{"key":"ref27","article-title":"Multi-agent generative adversarial imitation learning","author":"Song","year":"2018","journal-title":"Advances in neural information processing systems"},{"article-title":"Multi-agent adversarial inverse reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Yu","key":"ref28"},{"key":"ref29","article-title":"Training language models to follow instructions with human feedback","author":"Ouyang","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref30","article-title":"Open problems and fundamental limitations of reinforcement learning from human feedback","author":"Casper","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1219097111"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682321"},{"key":"ref33","article-title":"Spectral methods meet EM: A provably optimal algorithm for crowdsourcing","author":"Zhang","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2020.3045613"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26412-2_3"},{"key":"ref36","article-title":"Crowd-PrefRL: Preference-based reward learning from crowds","author":"Chhan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"MaxMin-RLHF: Towards equitable alignment of large language models with diverse human preferences","author":"Chakraborty","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Distributional preference learning: Understanding and accounting for hidden context in RLHF","author":"Siththaranjan","year":"2023","journal-title":"arXiv preprint"},{"article-title":"Imitation learning by estimating expertise of demonstrators","volume-title":"International Conference on Machine Learning","author":"Beliaev","key":"ref39"},{"key":"ref40","article-title":"Feudal reinforcement learning","author":"Dayan","year":"1992","journal-title":"Advances in neural information processing systems"},{"key":"ref41","article-title":"Reinforcement learning with hierarchies of machines","author":"Parr","year":"1997","journal-title":"Advances in neural information processing systems"},{"key":"ref42","article-title":"Modulated policy hierarchies","author":"Pashevich","year":"2018","journal-title":"Deep Reinforcement Learning Work-shop at Neural Information Processing Systems"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1613\/jair.639"},{"key":"ref44","article-title":"Hier-archical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","author":"Kulkarni","year":"2016","journal-title":"Advances in neural information processing systems"},{"article-title":"Feudal networks for hierarchical rein-forcement learning","volume-title":"International Conference on Machine Learning","author":"Vezhnevets","key":"ref45"},{"key":"ref46","article-title":"Learning goal embeddings via self-play for hierarchical reinforcement learning","author":"Sukhbaatar","year":"2018","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"Meta learning shared hierarchies","author":"Frans","year":"2017","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10744"},{"key":"ref50","article-title":"Data-efficient hierarchical reinforcement learning","author":"Nachum","year":"2018","journal-title":"Advances in neural information processing systems"},{"article-title":"Do as I can, not as I say: Grounding language in robotic affordances","volume-title":"Conference on Robot Learning","author":"Brohan","key":"ref51"},{"article-title":"PaLM-E: An embodied multimodal language model","volume-title":"International Conference on Machine Learning","author":"Driess","key":"ref52"},{"key":"ref53","article-title":"Voyager: An open-ended embodied agent with large language models","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s42113-020-00093-9"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460907"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-021-02726-3"},{"key":"ref57","article-title":"Hierarchical skills for efficient exploration","author":"Gehring","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Skill preferences: Learning to extract and execute robotic skills from human feedback","volume-title":"Conference on Robot Learning","author":"Wang","key":"ref58"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1177\/26339137231222481"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2019.12.182"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1900661"},{"article-title":"Communication in multi-agent rein-forcement learning: Intention sharing","volume-title":"International Conference on Learning Representations","author":"Kim","key":"ref62"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161244"},{"key":"ref64","article-title":"Multi-agent reinforcement learning via double averaging primal-dual optimization","author":"Wai","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Modeling others using oneself in multi-agent reinforcement learning","volume-title":"International conference on machine learning","author":"Raileanu","key":"ref65"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2018.01.002"},{"key":"ref67","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"issue":"1","key":"ref69","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref70","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.208"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.759"},{"article-title":"An explanation of in-context learning as implicit Bayesian inference","volume-title":"International Conference on Learning Representations","author":"Xie","key":"ref73"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/880"},{"article-title":"Guiding pretraining in reinforcement learning with large language models","volume-title":"International Conference on Machine Learning","author":"Du","key":"ref75"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2021.102891"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.3390\/systems10010015"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2018.2886671"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/3349537.3351892"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-40030-3_24"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2021.640647"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-020-00666-5"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/s10726-022-09792-z"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1613\/jair.5098"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1177\/0018720814547570"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1177\/0018720815581940"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1518\/hfes.46.1.50.30392"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1177\/00187208211047323"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1080\/1463922X.2022.2061080"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/3397481.3450656"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3173889"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858558"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2021.3086018"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.54941\/ahfe1003743"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1621147114"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.21236\/ad1166231"},{"key":"ref97","article-title":"A survey of explainable reinforcement learning","author":"Milani","year":"2022","journal-title":"arXiv preprint"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1391"},{"key":"ref99","article-title":"Visualization techniques for transparent human-agent interface designs","author":"Cha","year":"2019","journal-title":"tech. rep., ARL-TR-8674. US Combat Capabilities Development Command Army Research Laboratory Aberdeen Proving Ground"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372852"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445717"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1145\/3579605"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2018.07.007"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-91122-9_18"},{"article-title":"Learning human objectives by evaluating hypothetical behavior","volume-title":"International Conference on Machine Learning","author":"Reddy","key":"ref105"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161081"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1016\/bs.plm.2021.03.001"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2018.2864909"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1038\/nature14541"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1506.02142"},{"key":"ref111","article-title":"Sparks of artificial general intelligence: Early experiments with GPT-4","author":"Bubeck","year":"2023","journal-title":"arXiv preprint"},{"key":"ref112","article-title":"A very preliminary analysis of DALL-E 2","author":"Marcus","year":"2022","journal-title":"arXiv preprint"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1080\/09540091.2014.885279"},{"article-title":"AskWorld: Budget-sensitive query evaluation for knowledge-on-demand","volume-title":"International Joint Conference on Artificial Intelligence","author":"Samadi","key":"ref114"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2019.8847988"},{"article-title":"The greedy miser: Learning under test-time budgets","volume-title":"International Conference on Machine Learning","author":"Xu","key":"ref116"},{"article-title":"Pareto optimal streaming unsupervised classification","volume-title":"International Conference on Machine Learning","author":"Basu","key":"ref117"},{"article-title":"A general framework for multi-fidelity Bayesian optimization with Gaussian processes","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Song","key":"ref118"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30179-8_24"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v30i1.6657"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3187265"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10299-x"},{"key":"ref123","article-title":"Enhancing interoperability: The foundation for effective NATO operations","author":"Derleth","year":"2015","journal-title":"NATO Review"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1007\/s00034-019-01316-6"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636737"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3089120"}],"event":{"name":"2024 International Conference on Military Communication and Information Systems (ICMCIS)","start":{"date-parts":[[2024,4,23]]},"location":"Koblenz, Germany","end":{"date-parts":[[2024,4,24]]}},"container-title":["2024 International Conference on Military Communication and Information Systems (ICMCIS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10540649\/10540612\/10540933.pdf?arnumber=10540933","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,28]],"date-time":"2024-09-28T05:12:01Z","timestamp":1727500321000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10540933\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,23]]},"references-count":126,"URL":"https:\/\/doi.org\/10.1109\/icmcis61231.2024.10540933","relation":{},"subject":[],"published":{"date-parts":[[2024,4,23]]}}}