Publications

    2018

  • T. N. Hoang, Y. Xiao, K. Sivakumar, C. Amato, and J. How. Near-optimal adversarial policy switching for decentralized asynchronous multi-agent systems. In Proceedings of the International Conference on Robotics and Automation. 2018.
  • 2017

  • C. Amato, G. D. Konidaris, A. Anders, G. Cruz, J. P. How, and L. P. Kaelbling. Policy search for multi-robot coordination under uncertainty. The International Journal of Robotics Research, 2017.
  • S. Katt, F. A. Oliehoek, and C. Amato. Learning in POMDPs with Monte Carlo tree search. In Proceedings of the International Conference on Machine Learning, 1819–1827. 2017.
  • S. Omidshafiei, Ali-akbar Agha-mohammadi, C. Amato, and J. P. How. Decentralized control of multi-robot partially observable markov decision processes using belief space macro-actions. The International Journal of Robotics Research, 2017.
  • S. Omidshafiei, C. Amato, M. Liu, J. P. How, and J. Vian. Scalable accelerated decentralized multi-robot policy search in continuous observation spaces. In Proceedings of the International Conference on Robotics and Automation. 2017.
  • S. Omidshafiei, S.-Y. Liu, M. Everett, B. Lopez, C. Amato, M. Liu, J. P. How, and J. Vian. Semantic-level decentralized multi-robot decision-making using probabilistic macro-observations. In Proceedings of the International Conference on Robotics and Automation. 2017.
  • 2016

  • J. S. Dibangoye, C. Amato, O. Buffet, and F. Charpillet. Optimally solving Dec-POMDPs as continuous-state MDPs. Journal of Artificial Intelligence Research, 55:443–497, 2016.
  • M. Liu, C. Amato, E. Anesta, J. D. Griffith, and J. P. How. Learning for decentralized control of multiagent systems in large partially observable stochastic environments. In Proceedings of the AAAI Conference on Artificial Intelligence, 2523–2529. 2016.
  • F. A. Oliehoek and C. Amato. A Concise Introduction to Decentralized POMDPs. Springer, 2016.
  • S. Omidshafiei, Ali-akbar Agha-mohammadi, C. Amato, S.-Y. Liu, J. P. How, and J. Vian. Graph-based cross entropy method for solving multi-robot decentralized POMDPs. In Proceedings of the International Conference on Robotics and Automation. 2016.
  • 2015

  • C. Amato. Cooperative decision making. In M. J. Kochenderfer, editor, Decision Making Under Uncertainty: Theory and Application. MIT Press, 2015.
  • C. Amato, G. D. Konidaris, A. Anders, G. Cruz, J. P. How, and L. P. Kaelbling. Policy search for multi-robot coordination under uncertainty. In Robotics: Science and Systems. 2015.
  • C. Amato, G. D. Konidaris, G. Cruz, C. A. Maynor, J. P. How, and L. P. Kaelbling. Planning for decentralized control of multiple robots under uncertainty. In Proceedings of the International Conference on Robotics and Automation, 1241–1248. 2015.
  • C. Amato and F. A. Oliehoek. Scalable planning and learning for multiagent POMDPs. In Proceedings of the AAAI Conference on Artificial Intelligence. 2015.
  • M. Liu, C. Amato, X. Liao, L. Carin, and J. P. How. Stick-breaking policy learning in Dec-POMDPs. In Proceedings of the International Joint Conference on Artificial Intelligence, 2011–2017. 2015.
  • S. Omidshafiei, Ali-akbar Agha-mohammadi, C. Amato, and J. P. How. Decentralized control of partially observable Markov decision processes using belief space macro-actions. In Proceedings of the International Conference on Robotics and Automation, 5962–5969. 2015.
  • 2014

  • C. Amato, G. D. Konidaris, and L. P. Kaelbling. Planning with macro-actions in decentralized POMDPs. In Proceedings of the Conference on Autonomous Agents and Multiagent Systems. 2014.
  • J. S. Dibangoye, C. Amato, O. Buffet, and F. Charpillet. Exploiting separability in multi-agent planning with continuous-state MDPs. In Proceedings of the Conference on Autonomous Agents and Multiagent Systems. 2014.
  • F. A. Oliehoek and C. Amato. Best response Bayesian reinforcement learning for multiagent systems with state uncertainty. In Proceedings of the Workshop on Multi-Agent Sequential Decision Making in Uncertain Domains (MSDM) at AAMAS. 2014.
  • 2013

  • C. Amato, G. Chowdhary, A. Geramifard, N. K. Ure, and M. J. Kochenderfer. Decentralized control of partially observable Markov decision processes. In Proceedings of the Fifty-Second IEEE Conference on Decision and Control, 2398–2405. 2013.
  • C. Amato and F. A. Oliehoek. Bayesian reinforcement learning for multiagent systems with state uncertainty. In Proceedings of the Workshop on Multi-Agent Sequential Decision Making in Uncertain Domains (MSDM) at AAMAS, 76–83. 2013.
  • J. S. Dibangoye, C. Amato, O. Buffet, and F. Charpillet. Optimally solving Dec-POMDPs as continuous-state MDPs. In Proceedings of the International Joint Conference on Artificial Intelligence. Beijing, China, 2013.
  • J. S. Dibangoye, C. Amato, A. Doniec, and F. Charpillet. Producing efficient error-bounded solutions for transition independent decentralized MDPs. In Proceedings of the Conference on Autonomous Agents and Multiagent Systems. Saint Paul, MN, 2013.
  • F. A. Oliehoek, M. T. J. Spaan, C. Amato, and S. Whiteson. Incremental clustering and expansion for faster optimal planning in Dec-POMDPs. Journal of Artificial Intelligence Research, 46:449–509, 2013.
  • 2012

  • C. Amato and E. Brunskill. Diagnose and decide: an optimal bayesian approach. In Proceedings of the Workshop on Bayesian Optimization and Decision Making at NIPS. Lake Tahoe, Nevada, 2012.
  • J. S. Dibangoye, C. Amato, and A. Doniec. Scaling up decentralized MDPs through heuristic search. In Proceedings of the Thirty-First Conference on Uncertainty in Artificial Intelligence. Catalina Island, CA, 2012.
  • K. Kapoor, C. Amato, N. Srivastava, and P. Schrater. Using POMDPs to control an accuracy-processing time tradeoff in video surveillance. In Proceedings of the Twenty-Fourth Annual Conference on Innovative Applications of Artificial Intelligence. Toronto, Canada, 2012.
  • 2011

  • C. Amato, N. Schurr, and P. Picciano. Towards realistic decentralized modelling for use in a real-world personal assistant agent scenario. In Proceedings of the Workshop on Optimisation in Multi-Agent Systems at the Tenth International Conference on Autonomous Agents and Multi-Agent Systems. Taipei, Taiwan, 2011.
  • F. A. Oliehoek, M. T. J. Spaan, and C. Amato. Scaling up optimal heuristic search in Dec-POMDPs via incremental expansion. In Proceedings of the International Joint Conference on Artificial Intelligence. Barcelona, Spain, 2011.
  • P. Varakantham, N. Schurr, A. Carlin, and C. Amato. Adaptive decision support for structured organizations: a case for OrgPOMDPs. In Proceedings of the Conference on Autonomous Agents and Multiagent Systems. Taipei, Taiwan, 2011.
  • P. Varakantham, N. Schurr, A. Carlin, and C. Amato. Decision support in organizations: a case for OrgPOMDPs. In Proceedings of the Tenth IEEE/WIC/ACM International Conference on Intelligent Agent Technology. Lyon, France, 2011.
  • 2010

  • C. Amato. Increasing scalability in algorithms for centralized and decentralized partially observable Markov decision processes: efficient decision-making and coordination in uncertain environments. Technical Report UM-CS-PhD-2010-005, University of Massachusetts, Department of Computer Science, Amherst, MA, 2010.
  • C. Amato, D. S. Bernstein, and S. Zilberstein. Optimizing fixed-size stochastic controllers for POMDPs and decentralized POMDPs. Journal of Autonomous Agents and Multi-Agent Systems, 21(3):293–320, 2010.
  • C. Amato, B. Bonet, and S. Zilberstein. Finite-state controllers based on Mealy machines for centralized and decentralized POMDPs. In Proceedings of the AAAI Conference on Artificial Intelligence, 1052–1058. Atlanta, GA, 2010.
  • C. Amato and G. Shani. High-level reinforcement learning in strategy games. In Proceedings of the Conference on Autonomous Agents and Multiagent Systems. Toronto, Canada, 2010.
  • F. A. Oliehoek, M. T. J. Spaan, J. S. Dibangoye, and C. Amato. Solving identical payoff bayesian games with heuristic search. In Proceedings of the Conference on Autonomous Agents and Multiagent Systems. Toronto, Canada, 2010.
  • 2009

  • C. Amato, J. S. Dibangoye, and S. Zilberstein. Incremental policy generation for finite-horizon DEC-POMDPs. In Proceedings of the International Conference on Automated Planning and Scheduling, 2–9. Thessaloniki, Greece, 2009.
  • C. Amato and S. Zilberstein. Achieving goals in decentralized POMDPs. In Proceedings of the Conference on Autonomous Agents and Multiagent Systems, 593–600. Budapest, Hungary, 2009.
  • C. Amato and S. Zilberstein. Incremental policy generation for DEC-POMDPs. Technical Report UM-CS-2009-006, University of Massachusetts, Department of Computer Science, Amherst, MA, 2009.
  • D. S. Bernstein, C. Amato, E. A. Hansen, and S. Zilberstein. Policy iteration for decentralized control of Markov decision processes. Journal of Artificial Intelligence Research, 34:89–132, 2009.
  • 2008

  • C. Amato and S. Zilberstein. What's worth memorizing: attribute-based planning for DEC-POMDPs. In Proceedings of the Multiagent Planning Workshop, the Eighteenth International Conference on Automated Planning and Scheduling. Sydney, Australia, 2008.
  • D. S. Bernstein, C. Amato, E. A. Hansen, and S. Zilberstein. Policy iteration for decentralized control of Markov decision processes. Technical Report UM-CS-2008-044, University of Massachusetts, Department of Computer Science, Amherst, MA, 2008.
  • 2007

  • C. Amato, D. S. Bernstein, and S. Zilberstein. Optimizing fixed-size stochastic controllers for POMDPs and decentralized POMDPs. Technical Report UM-CS-2007-70, University of Massachusetts, Department of Computer Science, Amherst, MA, 2007.
  • C. Amato, D. S. Bernstein, and S. Zilberstein. Optimizing memory-bounded controllers for decentralized POMDPs. In Proceedings of the Thirty-First Conference on Uncertainty in Artificial Intelligence, 1–8. Vancouver, Canada, 2007.
  • C. Amato, D. S. Bernstein, and S. Zilberstein. Solving POMDPs using quadratically constrained linear programs. In Proceedings of the International Joint Conference on Artificial Intelligence, 2418–2424. Hyderabad, India, 2007.
  • C. Amato, A. Carlin, and S. Zilberstein. Bounded dynamic programming for decentralized POMDPs. In Proceedings of the Workshop on Multi-Agent Sequential Decision Making in Uncertain Domains, the Sixth International Joint Conference on Autonomous Agents and Multiagent Systems. Honolulu, Hawai'i, 2007.
  • 2006

  • C. Amato, D. S. Bernstein, and S. Zilberstein. Optimal fixed-size controllers for decentralized POMDPs. In Proceedings of the Workshop on Multi-Agent Sequential Decision Making in Uncertain Domains (MSDM) at AAMAS. Hakodate, Japan, 2006.
  • C. Amato, D. S. Bernstein, and S. Zilberstein. Solving POMDPs using quadratically constrained linear programs. In Proceedings of the Ninth International Symposium on Artificial Intelligence and Mathematics. Fort Lauderdale, FL, 2006.
  • 2004

  • D. S. Bernstein, E. A. Hansen, S. Zilberstein, and C. Amato. Dynamic programming for partially observable stochastic games. In Proceedings of the AAAI Spring Symposium on Bridging the Multi-Agent and Multi-Robotic Research Gap. Stanford, California, 2004.