{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T22:40:56Z","timestamp":1762641656828,"version":"3.28.0"},"reference-count":22,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,6]]},"DOI":"10.1109\/acc.2014.6859242","type":"proceedings-article","created":{"date-parts":[[2014,7,29]],"date-time":"2014-07-29T21:01:49Z","timestamp":1406667709000},"page":"1279-1285","source":"Crossref","is-referenced-by-count":15,"title":["Planning for large-scale multiagent problems via hierarchical decomposition with applications to UAV health management"],"prefix":"10.1109","author":[{"given":"Yu Fan","family":"Chen","sequence":"first","affiliation":[]},{"given":"N. Kemal","family":"Ure","sequence":"additional","affiliation":[]},{"given":"Girish","family":"Chowdhary","sequence":"additional","affiliation":[]},{"given":"Jonathan P.","family":"How","sequence":"additional","affiliation":[]},{"given":"John","family":"Vian","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"19","article-title":"Health-aware decentralized planning and learning for large-scale multiagent missions","author":"ure","year":"2013","journal-title":"Conference on Guidance Navigation and Control"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2013.6580186"},{"key":"17","article-title":"Hierarchical solution of markov decision processes using macroactions","author":"hauskrecht","year":"1998","journal-title":"Proceedings of the Fourteenth Conference on Uncertainty in Artificial Intelligence"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.2514\/6.2012-4622"},{"key":"15","article-title":"Greedy algorithms for sparse reinforcement learning","author":"painter-wakefield","year":"2012","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"16","article-title":"Coordinated reinforcement learning","author":"guestrin","year":"2002","journal-title":"ICML"},{"key":"13","doi-asserted-by":"crossref","DOI":"10.1201\/9781439821091","author":"busoniu","year":"2010","journal-title":"Reinforcement Learning and Dynamic Programming Using Function Approximators"},{"journal-title":"Practical Reinforcement Learning Using Representation Learning and Safe Exploration for Large Scale Markov Decision Processes","year":"2012","author":"geramifard","key":"14"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1016\/S0019-9958(58)80003-0"},{"journal-title":"Dynamic Programming and Optimal Control","year":"2005","author":"bertsekas","key":"12"},{"journal-title":"Dynamic Programming","year":"2003","author":"bellman","key":"21"},{"key":"3","first-page":"1757","article-title":"Learning from multiple sources","volume":"9","author":"crammer","year":"2008","journal-title":"The Journal of Machine Learning Research"},{"key":"20","doi-asserted-by":"crossref","DOI":"10.1613\/jair.1497","article-title":"Solving transition independent decentralized Markov decision processes","volume":"22","author":"becker","year":"2004","journal-title":"Journal of Artificial Intelligence Research"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008807102993"},{"journal-title":"Issues in multiagent resource allocation","year":"2005","author":"chevaleyre","key":"1"},{"journal-title":"Approximate Multi-Agent Planning in Dynamic and Uncertain Environments","year":"2012","author":"redding","key":"10"},{"key":"7","article-title":"Multiagent planning with factored MDPs","author":"guestrin","year":"2001","journal-title":"NIPS"},{"key":"6","article-title":"Sequential optimality and coordination in multiagent systems","author":"boutilier","year":"1999","journal-title":"IJCAI"},{"key":"5","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"4","first-page":"671","article-title":"Packet routing in dynamically changing networks: A reinforcement learning approach","author":"boyan","year":"1994","journal-title":"Advances in neural information processing systems"},{"key":"9","first-page":"1789","article-title":"Collaborative multiagent reinforcement learning by payoff propagation","volume":"7","author":"kok","year":"2006","journal-title":"The Journal of Machine Learning Research"},{"key":"8","article-title":"Graphical models in continuous domains for multiagent reinforcement learning","author":"proper","year":"2013","journal-title":"Proceedings of the 2013 International Conference on Autonomous Agents and Multi-agent Systems"}],"event":{"name":"2014 American Control Conference - ACC 2014","start":{"date-parts":[[2014,6,4]]},"location":"Portland, OR, USA","end":{"date-parts":[[2014,6,6]]}},"container-title":["2014 American Control Conference"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6849600\/6858556\/06859242.pdf?arnumber=6859242","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,13]],"date-time":"2022-04-13T01:25:10Z","timestamp":1649813110000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6859242\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,6]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/acc.2014.6859242","relation":{},"subject":[],"published":{"date-parts":[[2014,6]]}}}