{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T22:06:56Z","timestamp":1729634816794,"version":"3.28.0"},"reference-count":22,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1109\/adprl.2014.7010642","type":"proceedings-article","created":{"date-parts":[[2015,1,19]],"date-time":"2015-01-19T21:48:03Z","timestamp":1421704083000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Heuristics for multiagent reinforcement learning in decentralized decision problems"],"prefix":"10.1109","author":[{"given":"Martin W.","family":"Allen","sequence":"first","affiliation":[]},{"given":"David","family":"Hahn","sequence":"additional","affiliation":[]},{"given":"Douglas C.","family":"MacFarland","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(02)00378-8"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1287\/moor.27.4.819.297"},{"key":"ref12","first-page":"955","article-title":"Distributed model shaping for scaling to decentralized POMDPs with hundreds of agents","author":"velagapudi","year":"2011","journal-title":"Proc Int Joint Conf Autonomous Agents and Multiagent Systems"},{"key":"ref13","first-page":"423","article-title":"Solving transition independent decentralized MDPs","volume":"22","author":"becker","year":"2004","journal-title":"J AI Research"},{"key":"ref14","first-page":"19","article-title":"Complexity of decentralized control: Special cases","author":"allen","year":"2009","journal-title":"Advances in neural information processing systems"},{"key":"ref15","first-page":"1287","article-title":"Bounded policy iteration for decentralized POMDPs","author":"bernstein","year":"2005","journal-title":"Intl Joint Conf on AI"},{"key":"ref16","first-page":"746","article-title":"The dynamics of reinforcement learning in cooperative multiagent systems","author":"claus","year":"1998","journal-title":"National AIIE Conf"},{"key":"ref17","first-page":"326","article-title":"Reinforcement learning of coordination in cooperative multi-agent systems","author":"kapetanakis","year":"2002","journal-title":"National AIIE Conf"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref4","first-page":"18","article-title":"Mixed integer linear programming for exact finite-horizon planning in decentralized POMDPs","author":"aras","year":"2007","journal-title":"Proc Int l Conf Automated Planning and Scheduling"},{"key":"ref3","first-page":"709","article-title":"Dynamic programming for partially observable stochastic games","author":"hansen","year":"2004","journal-title":"National AIIE Conf"},{"key":"ref6","article-title":"Improved memory-bounded dynamic programming for decentralized POMDPs","author":"seuken","year":"2007","journal-title":"Conf on Uncertainty in AI"},{"key":"ref5","first-page":"449","article-title":"Incremental clustering and expansion for faster optimal planning in Dec-POMDPs","volume":"46","author":"oliehoek","year":"2013","journal-title":"J AI Research"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_15"},{"key":"ref7","first-page":"501","article-title":"Value-based observation compression for DEC-POMDPs","author":"carlin","year":"2008","journal-title":"Proc Int Joint Conf Autonomous Agents and Multiagent Systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-007-9026-5"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/18.61115"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.1946.0056"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"}],"event":{"name":"2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","start":{"date-parts":[[2014,12,9]]},"location":"Orlando, FL, USA","end":{"date-parts":[[2014,12,12]]}},"container-title":["2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7000183\/7010603\/07010642.pdf?arnumber=7010642","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,26]],"date-time":"2022-04-26T21:47:34Z","timestamp":1651009654000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7010642\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,12]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/adprl.2014.7010642","relation":{},"subject":[],"published":{"date-parts":[[2014,12]]}}}