{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,27]],"date-time":"2024-12-27T05:16:02Z","timestamp":1735276562866,"version":"3.32.0"},"reference-count":58,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006831","name":"United States Air Force","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006831","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10803062","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"14172-14179","source":"Crossref","is-referenced-by-count":0,"title":["Competitive Multi-Team Behavior in Dynamic Flight Scenarios"],"prefix":"10.1109","author":[{"given":"Tim","family":"Seyde","sequence":"first","affiliation":[{"name":"Massachusetts Institute of Technology,Computer Science and Artificial Intelligence Laboratory (CSAIL),USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mathias","family":"Lechner","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology,Computer Science and Artificial Intelligence Laboratory (CSAIL),USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joshua","family":"Rountree","sequence":"additional","affiliation":[{"name":"MIT AI Accelerator,Department of the Air Force,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniela","family":"Rus","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology,Computer Science and Artificial Intelligence Laboratory (CSAIL),USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1037\/e663212010-001","article-title":"Overcoming information overload in the cockpit","volume-title":"Operations Research Center of Excellence, West Point, NY. ORCEN Technical report: DSE-TR-0904","author":"Deveans","year":"2009"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.29007\/91x9"},{"article-title":"JAX: composable transformations of Python+NumPy programs","year":"2018","author":"Bradbury","key":"ref3"},{"key":"ref4","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11371"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-51497-5_4"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1126\/science.add4679"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5878"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi8022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"article-title":"Dota 2 with large scale deep reinforcement learning","year":"2019","author":"Berner","key":"ref12"},{"key":"ref13","article-title":"The StarCraft Multi-Agent Challenge","author":"Samvelyan","year":"2019","journal-title":"CoRR"},{"article-title":"Smacv2: An improved benchmark for cooperative multi-agent reinforcement learning","year":"2022","author":"Ellis","key":"ref14"},{"article-title":"Dynamic multi-team racing: Competitive driving on 1\/10-th scale vehicles via learning in simulation","volume-title":"7th Annual Conference on Robot Learning","author":"Werner","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MRS60187.2023.10416792"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3270444"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968116"},{"key":"ref19","first-page":"1147","article-title":"Flightmare: A flexible quadrotor simulator","volume-title":"Proceedings of the 2020 Conference on Robot Learning","author":"Song"},{"key":"ref20","article-title":"Airsim: High-fidelity visual and physical simulation for autonomous vehicles","volume-title":"Field and Service Robotics","author":"Shah","year":"2017"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635857"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCA51439.2020.9264567"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.2514\/6.2004-4923"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10160342"},{"key":"ref25","first-page":"16 455","article-title":"Discovered policy optimisation","volume":"35","author":"Lu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.085"},{"article-title":"Jaxmarl: Multi-agent rl environments in jax","year":"2023","author":"Rutherford","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-09996-w"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref31","first-page":"2","article-title":"The dynamics of reinforcement learning in cooperative multiagent systems","volume":"1998","author":"Claus","year":"1998","journal-title":"AAAI\/IAAI"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888912000057"},{"key":"ref33","article-title":"Distributed value functions","author":"Schneider","year":"1999","journal-title":"ICML"},{"key":"ref34","first-page":"656","article-title":"Q-decomposition for reinforcement learning agents","volume-title":"Proceedings of the 20th International Conference on Machine Learning (ICML-03)","author":"Russell"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981441"},{"key":"ref36","first-page":"4295","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Rashid"},{"key":"ref37","first-page":"5887","article-title":"Qtran: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Son"},{"article-title":"Learning to represent action values as a hypergraph on the action vertices","year":"2020","author":"Tavakoli","key":"ref38"},{"article-title":"Solving continuous control via q-learning","volume-title":"The Eleventh International Conference on Learning Representations","author":"Seyde","key":"ref39"},{"article-title":"Dop: Off-policy multi-agent decomposed policy gradients","volume-title":"International Conference on Learning Representations","author":"Wang","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17353"},{"key":"ref42","article-title":"FACMAC: Factored multi-agent centralised policy gradients","volume-title":"Advances in Neural Information Processing Systems","author":"Peng","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICUAS51884.2021.9476700"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2017.11.014"},{"article-title":"Compositional transfer in hierarchical reinforcement learning","year":"2019","author":"Wulfmeier","key":"ref45"},{"article-title":"A hierarchical approach for strategic motion planning in autonomous racing","year":"2022","author":"Reiter","key":"ref46"},{"article-title":"Hierarchical control for cooperative teams in competitive autonomous racing","year":"2022","author":"Thakkar","key":"ref47"},{"key":"ref48","doi-asserted-by":"crossref","DOI":"10.1002\/9781119174882","volume-title":"Aircraft control and simulation: dynamics, controls design, and autonomous systems","author":"Stevens","year":"2015"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.1998.703559"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"article-title":"Option-critic in cooperative multi-agent systems","year":"2019","author":"Chakravorty","key":"ref51"},{"key":"ref52","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems","author":"Sunehag"},{"key":"ref53","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"International conference on machine learning","author":"Bellemare"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref54"},{"key":"ref55","article-title":"Next-generation airborne collision avoidance system","author":"Kochenderfer","year":"2012","journal-title":"Massachusetts Institute of Technology-Lincoln Laboratory Lexington United States, Tech. Rep."},{"key":"ref56","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume-title":"International conference on machine learning","author":"Iqbal"},{"key":"ref57","article-title":"Deep reinforcement learning at the edge of the statistical precipice","author":"Agarwal","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref58","article-title":"Gigastep-one billion steps per second multi-agent reinforcement learning","volume":"36","author":"Lechner","year":"2024","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2024,10,14]]},"location":"Abu Dhabi, United Arab Emirates","end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10803062.pdf?arnumber=10803062","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T06:54:01Z","timestamp":1735196041000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10803062\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10803062","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}