{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,17]],"date-time":"2025-05-17T05:26:02Z","timestamp":1747459562345,"version":"3.37.3"},"reference-count":28,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"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"}]},{"DOI":"10.13039\/100004726","name":"Raytheon Company","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004726","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2021,10]]},"DOI":"10.1109\/lra.2021.3096758","type":"journal-article","created":{"date-parts":[[2021,7,26]],"date-time":"2021-07-26T21:32:17Z","timestamp":1627335137000},"page":"6868-6875","source":"Crossref","is-referenced-by-count":12,"title":["Neural Tree Expansion for Multi-Robot Planning in Non-Cooperative Environments"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4189-4090","authenticated-orcid":false,"given":"Benjamin","family":"Riviere","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0773-028X","authenticated-orcid":false,"given":"Wolfgang","family":"Honig","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthew","family":"Anderson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6657-3907","authenticated-orcid":false,"given":"Soon-Jo","family":"Chung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"1","article-title":"A0C: Alpha zero in continuous action space","author":"moerland","year":"2018","journal-title":"Proc of European Workshop on Reinforcement Learning"},{"key":"ref11","article-title":"Learning to plan in high dimensions via neural exploration-exploitation trees","author":"chen","year":"2020","journal-title":"Int Conf Lear Repres"},{"key":"ref12","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"2011","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref13","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"99","author":"sutton","year":"1999","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref14","article-title":"Competitive policy optimization","author":"prajapat","year":"2020","journal-title":"CoRR"},{"journal-title":"Differential Games A Mathematical Theory With Applications to Warfare and Pursuit Control and Optimization","year":"1965","author":"isaacs","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2994023"},{"article-title":"Matching-based capture strategies for 3D heterogeneous multiplayer reach-avoid differential games","year":"2019","author":"yan","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2018.2853610"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2020.3018549"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989376"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2012.2186810"},{"key":"ref27","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"paszke","year":"2019","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/10187.001.0001"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3393691.3394202"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/11871842_29"},{"key":"ref8","first-page":"335","article-title":"Sample-based planning for continuous action Markov decision processes, and scheduling","author":"mansley","year":"2011","journal-title":"Proc Int Conf oAutom Plan Scheduling"},{"key":"ref7","first-page":"1","article-title":"POLY-HOOT: Monte-Carlo planning in continuous space MDPs with non-asymptotic analysis","author":"mao","year":"2020","journal-title":"Neural Inf Process Syst"},{"key":"ref2","first-page":"1496","article-title":"Control strategies for multiplayer targetattacker- defender differential games with double integrator dynamics","author":"coon","year":"2017","journal-title":"Proc IEEE 56th Annu Conf Decis Control"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40988-2_13"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2857004"},{"key":"ref22","first-page":"259","article-title":"Online algorithms for POMDPs with continuous state, action, and observation spaces","author":"sunberg","year":"2018","journal-title":"Proc Int Conf Autom Plann Scheduling"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2972818"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2994035"},{"key":"ref23","first-page":"482","article-title":"Reverse curriculum generation for reinforcement learning","volume":"78","author":"florensa","year":"2017","journal-title":"Proc Conf Robot Learn"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460730"},{"key":"ref25","first-page":"3391","article-title":"Deep sets","author":"zaheer","year":"2017","journal-title":"Proc Neural Inf Process Syst"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9475905\/09484771.pdf?arnumber=9484771","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:54:07Z","timestamp":1652194447000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9484771\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10]]},"references-count":28,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/lra.2021.3096758","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"type":"electronic","value":"2377-3766"},{"type":"electronic","value":"2377-3774"}],"subject":[],"published":{"date-parts":[[2021,10]]}}}