{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:13:07Z","timestamp":1780053187520,"version":"3.54.0"},"reference-count":90,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,12]]},"DOI":"10.1109\/cdc.2013.6760239","type":"proceedings-article","created":{"date-parts":[[2014,3,13]],"date-time":"2014-03-13T22:14:07Z","timestamp":1394748847000},"page":"2398-2405","source":"Crossref","is-referenced-by-count":86,"title":["Decentralized control of partially observable Markov decision processes"],"prefix":"10.1109","author":[{"given":"Christopher","family":"Amato","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Girish","family":"Chowdhary","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alborz","family":"Geramifard","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"N. Kemal","family":"Ure","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mykel J.","family":"Kochenderfer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"79","article-title":"Planetary rover control as a markov decision process","author":"bernstein","year":"2001","journal-title":"Proceedings of the the Sixth International Symposium on Artificial Intelligence Robotics and Automation in Space"},{"key":"78","doi-asserted-by":"crossref","DOI":"10.1609\/icaps.v19i1.13366","article-title":"Multi-agent online planning with communication","author":"wu","year":"2009","journal-title":"Proceedings of the Nineteenth International Conference on Automated Planning and Scheduling"},{"key":"77","first-page":"338","article-title":"Multiagent planning under uncertainty with stochastic communication delays","author":"spaan","year":"2008","journal-title":"Proceedings of the Eighteenth International Conference on Automated Planning and Scheduling"},{"key":"35","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(02)00378-8"},{"key":"36","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-007-9026-5"},{"key":"33","doi-asserted-by":"publisher","DOI":"10.1287\/moor.12.3.441"},{"key":"34","first-page":"19","article-title":"Complexity of decentralized control: Special cases","volume":"22","author":"allen","year":"2009","journal-title":"Advances in Neural Information Processing Systems Ser"},{"key":"39","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1609\/icaps.v19i1.13355","article-title":"Incremental policy generation for finite-horizon DEC-POMDPs","author":"amato","year":"2009","journal-title":"Proceedings of the Nineteenth International Conference on Automated Planning and Scheduling"},{"key":"37","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1613\/jair.2667","article-title":"Policy iteration for decentralized control of markov decision processes","volume":"34","author":"bernstein","year":"2009","journal-title":"Journal of Artificial Intelligence Research"},{"key":"38","first-page":"709","article-title":"Dynamic programming for partially observable stochastic games","author":"hansen","year":"2004","journal-title":"Proceedings of The Nineteenth National Conference on Artificial Intelligence"},{"key":"43","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1613\/jair.2447","article-title":"Optimal and approximate q-value functions for decentralized POMDPs","volume":"32","author":"oliehoek","year":"2008","journal-title":"Journal of Artificial Intelligence Research"},{"key":"42","doi-asserted-by":"publisher","DOI":"10.1109\/TSSC.1968.300136"},{"key":"41","article-title":"MAA*: A heuristic search algorithm for solving decentralized POMDPs","author":"szer","year":"2005","journal-title":"Proceedings of the twenty-first Conference on Uncertainty in Artificial Intelligence"},{"key":"40","article-title":"Exact dynamic programming for decentralized POMDPs with lossless policy compression","author":"boularias","year":"2008","journal-title":"Proceedings of the Eighteenth International Conference on Automated Planning and Scheduling"},{"key":"82","article-title":"An approximate dynamic programming approach to decentralized control of stochastic systems","author":"cogill","year":"2004","journal-title":"Proceedings of the Forty-Second Allerton Conference on Communication Control and Computing"},{"key":"83","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.1996.574318"},{"key":"80","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2005.1570273"},{"key":"81","article-title":"Coordinated multirobot exploration under communication constraints using decentralized markov decision processes","author":"matignon","year":"2012","journal-title":"Proceedings of the Twenty-Sixth AAAI Conference on Artificial Intelligence"},{"key":"86","first-page":"833","article-title":"Multi-agent systems by incremental gradient reinforcement learning","author":"dutech","year":"2001","journal-title":"Proceedings of the Seventeenth International Joint Conference on Artificial Intelligence"},{"key":"87","first-page":"489","article-title":"Learning to cooperate via policy search","author":"peshkin","year":"2000","journal-title":"Proceedings of the Sixteenth Conference on Uncertainty in Artificial Intelligence"},{"key":"84","doi-asserted-by":"publisher","DOI":"10.1145\/2486001.2486020"},{"key":"85","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2002.1007796"},{"key":"67","article-title":"Not all agents are equal: Scaling up distributed POMDPs for agent networks","author":"marecki","year":"2008","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"66","doi-asserted-by":"crossref","DOI":"10.1145\/1329125.1329388","article-title":"Letting loose a SPIDER on a network of POMDPs: Generating quality guaranteed policies","author":"varakantham","year":"2007","journal-title":"Proceedings of the Sixth International Conference on Autonomous Agents and Multiagent Systems"},{"key":"69","article-title":"Exploiting locality of interaction in factored dec-POMDPs","author":"oliehoek","year":"2008","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"68","first-page":"2140","article-title":"Scalable multiagent planning using probabilistic inference","volume":"201","author":"kumar","year":"0","journal-title":"Proceedings of the Twenty- Second International Joint Conference on Artificial Intelligence"},{"key":"22","first-page":"561","article-title":"Constraint-based dynamic programming for decentralized POMDPs with structured interactions","author":"kumar","year":"2009","journal-title":"Proceedings of the Eighth International Conference on Autonomous Agents and Multiagent Systems"},{"key":"23","first-page":"201","article-title":"Event-detecting multi-agent mdps: Complexity and constantfactor approximation","author":"kumar","year":"2009","journal-title":"Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence"},{"key":"24","article-title":"An extension of bayesian game approximation to partially observable stochastic games with competition and cooperation","author":"shi","year":"2010","journal-title":"International Conference on Artificial Intelligence"},{"key":"25","first-page":"478","article-title":"Sequential optimality and coordination in multiagent systems","author":"boutilier","year":"1999","journal-title":"Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence"},{"key":"26","first-page":"1523","article-title":"Multiagent planning with factored MDPs","volume":"15","author":"guestrin","year":"2001","journal-title":"Advances in Neural Information Processing Systems Ser"},{"key":"27","first-page":"253","article-title":"Context specific multiagent coordination and planning with factored MDPs","author":"guestrin","year":"2002","journal-title":"Proceedings of the Eighteenth National Conference on Artificial Intelligence"},{"key":"28","first-page":"1415","article-title":"Tree-based solution methods for multiagent POMDPs with delayed communication","author":"oliehoek","year":"2012","journal-title":"Proceedings of the Twenty-Sixth AAAI Conference on Artificial Intelligence"},{"key":"29","doi-asserted-by":"crossref","DOI":"10.1145\/860575.860598","article-title":"Optimizing information exchange in cooperative multi-agent systems","author":"goldman","year":"2003","journal-title":"Proceedings of the Second International Conference on Autonomous Agents and Multiagent Systems"},{"key":"3","author":"bryson","year":"1969","journal-title":"Applied Optimal Control"},{"key":"2","doi-asserted-by":"crossref","DOI":"10.1201\/9781439821091","author":"busoniu","year":"2010","journal-title":"Reinforcement Learning and Dynamic Programming Using Function Approximators"},{"key":"1","volume":"1 2","author":"bertsekas","year":"2007","journal-title":"Dynamic Programming and Optimal Control"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1016\/0022-247X(65)90154-X"},{"key":"30","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1613\/jair.1427","article-title":"Decentralized control of cooperative systems: Categorization and complexity analysis","volume":"22","author":"goldman","year":"2004","journal-title":"Journal of Artificial Intelligence Research"},{"key":"6","author":"bellman","year":"1957","journal-title":"Dynamic Programming"},{"key":"5","author":"howard","year":"1960","journal-title":"Dynamic Programming and Markov Processes"},{"key":"32","doi-asserted-by":"crossref","first-page":"423","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":"4","author":"stengel","year":"1986","journal-title":"Stochastic Optimal Control Theory and Application"},{"key":"31","author":"papadimitriou","year":"1994","journal-title":"Computational Complexity"},{"key":"70","first-page":"29","article-title":"Towards a unifying characterization for quantifying weak coupling in dec-POMDPs","author":"witwicki","year":"2011","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"71","first-page":"525","article-title":"Interaction-driven markov games for decentralized multiagent planning under uncertainty","author":"spaan","year":"2008","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"9","first-page":"754","article-title":"Partially observable markov decision processes","author":"poupart","year":"2010","journal-title":"Encyclopedia of Machine Learning"},{"key":"72","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1609\/icaps.v19i1.13369","article-title":"Exploiting coordination locales in distributed POMDPs via social model shaping","author":"varakantham","year":"2009","journal-title":"Proceedings of the Nineteenth International Conference on Automated Planning and Scheduling"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"73","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2011.05.001"},{"key":"74","doi-asserted-by":"crossref","DOI":"10.1145\/1082473.1082593","article-title":"Reasoning about joint beliefs for execution-time communication decisions","author":"roth","year":"2005","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"75","first-page":"1098","article-title":"Communication for improving policy computation in distributed POMDPs","author":"nair","year":"2004","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"76","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8640.2008.01329.x"},{"key":"59","first-page":"294","article-title":"Anytime planning for decentralized POMDPs using expectation maximization","author":"kumar","year":"2010","journal-title":"Proceedings of the Twenty-Sixth Conference on Uncertainty in Artificial Intelligence"},{"key":"58","doi-asserted-by":"crossref","first-page":"1052","DOI":"10.1609\/aaai.v24i1.7748","article-title":"Finite-state controllers based on mealy machines for centralized and decentralized POMDPs","author":"amato","year":"2010","journal-title":"Proceedings of the Twenty-Fourth AAAI Conference on Artificial Intelligence"},{"key":"57","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-009-9103-z"},{"key":"56","first-page":"1287","article-title":"Bounded policy iteration for decentralized POMDPs","author":"bernstein","year":"2005","journal-title":"Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence"},{"key":"19","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(01)00070-X"},{"key":"55","first-page":"389","article-title":"An optimal best-first search algorithm for solving infinite horizon DEC-POMDPs","author":"szer","year":"2005","journal-title":"Proceedings of the Sixteenth European Conference on Machine Learning"},{"key":"17","author":"egerstedt","year":"2010","journal-title":"Graph Theoretic Methods in Multiagent Networks"},{"key":"18","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1613\/jair.1024","article-title":"The communicative multiagent team decision problem: Analyzing teamwork theories and models","volume":"16","author":"pynadath","year":"2002","journal-title":"Journal of Artificial Intelligence Research"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1287\/moor.27.4.819.297"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2003.812781"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2009.06.006"},{"key":"14","year":"2002","journal-title":"Unmanned Aerial Vehicles Roadmap 2002-2027"},{"key":"11","author":"bryson","year":"2002","journal-title":"Applied Linear Optimal Control Examples and Algorithms"},{"key":"12","doi-asserted-by":"crossref","DOI":"10.1115\/1.2766721","article-title":"Recent research in cooperative control of multi-vehicle systems","author":"murray","year":"2007","journal-title":"ASME Journal of Dynamic Systems Measurement and Control"},{"key":"21","article-title":"Networked distributed pomdps: A synthesis of distributed constraint optimization and POMDPs","author":"nair","year":"2005","journal-title":"proceedings of the Twentieth National Conference on Artificial Intelligence"},{"key":"20","author":"khalil","year":"2002","journal-title":"Nonlinear Systems"},{"key":"64","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1613\/jair.2673","article-title":"A bilinear programming approach for multiagent planning","volume":"35","author":"petrik","year":"2009","journal-title":"Journal of Artificial Intelligence Research"},{"key":"65","article-title":"Producing efficient error-bounded solutions for transition independent decentralized MDPs","author":"dibangoye","year":"2013","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"62","article-title":"Bounded dynamic programming for decentralized POMDPs","author":"amato","year":"2007","journal-title":"Proceedings of the Workshop on Multi-Agent Sequential Decision Making in Uncertain Domains the Sixth International Joint Conference on Autonomous Agents and Multiagent Systems"},{"key":"63","first-page":"593","article-title":"Achieving goals in decentralized POMDPs","author":"amato","year":"2009","journal-title":"Proceedings of the Eighth International Conference on Autonomous Agents and Multiagent Systems"},{"key":"60","first-page":"2636","article-title":"Periodic finite state controllers for efficient POMDP and dec-POMDp planning","volume":"24","author":"pajarinen","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"61","first-page":"325","article-title":"Efficient planning for factored infinitehorizon dec-pomdps","author":"pajarinen","year":"2011","journal-title":"Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence"},{"key":"49","first-page":"344","article-title":"Improved memory-bounded dynamic programming for decentralized POMDPs","author":"seuken","year":"2007","journal-title":"Proceedings of the Twenty-Third Conference on Uncertainty in Artificial Intelligence"},{"key":"48","first-page":"2009","article-title":"Memory-bounded dynamic programming for DEC-POMDPs","author":"seuken","year":"2007","journal-title":"Proceedings of the Twentieth International Joint Conference on Artificial Intelligence"},{"key":"45","article-title":"Optimally solving dec-pomdps as continuous-state MDPs","author":"dibangoye","year":"2013","journal-title":"Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence"},{"key":"44","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1613\/jair.3804","article-title":"Incremental clustering and expansion for faster optimal planning in dec- POMDPs","volume":"46","author":"oliehoek","year":"2013","journal-title":"Journal of Artificial Intelligence Research"},{"key":"47","first-page":"1997","article-title":"Average-reward decentralized markov decision processes","author":"petrik","year":"2007","journal-title":"Proceedings of the Twentieth International Joint Conference on Artificial Intelligence"},{"key":"46","first-page":"18","article-title":"Mixed integer linear programming for exact finite-horizon planning in decentralized POMDPs","author":"aras","year":"2007","journal-title":"Proceedings of the Seventeenth International Conference on Automated Planning and Scheduling"},{"key":"90","article-title":"Coordinating multi-agent reinforcement learning with limited communication","author":"zhang","year":"2013","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-012-9200-2"},{"key":"51","article-title":"Point-based incremental pruning heuristic for solving finite-horizon DEC-POMDPs","author":"dibangoye","year":"2009","journal-title":"Proceedings of the Eighth International Conference on Autonomous Agents and Multiagent Systems"},{"key":"52","first-page":"1315","article-title":"Point-based backup for decentralized POMDPs: Complexity and new algorithms","author":"kumar","year":"2010","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"53","first-page":"1307","article-title":"Point-based policy generation for decentralized POMDPs","author":"wu","year":"2010","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"54","first-page":"705","article-title":"Taming decentralized POMDPs: Towards efficient policy computation for multiagent settings","author":"nair","year":"2003","journal-title":"Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence"},{"key":"88","article-title":"All learning is local: Multi-agent learning in global reward games","volume":"16","author":"chang","year":"2004","journal-title":"Advances in neural information processing systems"},{"key":"89","article-title":"Coordinated multi-agent reinforcement learning in networked distributed POMDPs","author":"zhang","year":"2011","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"50","article-title":"Value-based observation compression for DEC-POMDPs","author":"carlin","year":"2008","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"}],"event":{"name":"2013 IEEE 52nd Annual Conference on Decision and Control (CDC)","location":"Firenze","start":{"date-parts":[[2013,12,10]]},"end":{"date-parts":[[2013,12,13]]}},"container-title":["52nd IEEE Conference on Decision and Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6749719\/6759837\/06760239.pdf?arnumber=6760239","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,11]],"date-time":"2023-07-11T05:29:00Z","timestamp":1689053340000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6760239\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,12]]},"references-count":90,"URL":"https:\/\/doi.org\/10.1109\/cdc.2013.6760239","relation":{},"subject":[],"published":{"date-parts":[[2013,12]]}}}