Publications

2018[ top ]

Privacy-Preserving Policy Iteration for Decentralized POMDPs.
F. Wu, S. Zilberstein, and X. Chen. Proceedings of the Thirty-Second Conference on Artificial Intelligence (AAAI), 4759-4766, New Orleans, Lousiana, 2018. [abs] [bib] [pdf]
Integrated Cooperation and Competition in Multi-Agent Decision-Making.
K.H. Wray, A. Kumar, and S. Zilberstein. Proceedings of the Thirty-Second Conference on Artificial Intelligence (AAAI), 4751-4758, New Orleans, Lousiana, 2018. [abs] [bib] [pdf]
Towards Quicker Probabilistic Recognition with Multiple Goal Heuristic Search.
R.G. Freedman, Y. Fung, R. Ganchin, and S. Zilberstein. AAAI Workshop on Plan, Activity, and Intent Recognition (PAIR), New Orleans, Lousiana, 2018. [abs] [bib] [pdf]
Roles that Plan, Activity, and Intent Recognition with Planning Can Play in Games
R.G. Freedman and S. Zilberstein. AAAI Workshop on Knowledge Extraction from Games (KEG), New Orleans, Lousiana, 2018. [abs] [bib] [pdf]
An Anytime Algorithm for Task and Motion MDPs.
S. Srivastava, N. Desai, R.G. Freedman, and S. Zilberstein ICAPS Workshop on Planning and Robotics (PlanRob), Delft, The Netherlands, 2018. [abs] [bib] [pdf]
Relaxed Modification Heuristics for Equi-Reward Utility Maximizing Design.
S. Keren, L. Pineda, A. Gal, E. Karpas, and S. Zilberstein. ICAPS Workshop on Heuristics and Search for Domain-independent Planning (HSDIP), Delft, The Netherlands, 2018. [abs] [bib] [pdf]
Planning Using a Portfolio of Reduced Models.
S. Saisubramanian, S. Zilberstein, and P. Shenoy. Proceedings of the Seventeenth International Conference on Autonomous Agents and Multiagent Systems (AAMAS), Stockholm, Sweden, 2018. [abs] [bib] [pdf]
Safe Reduced Models for Probabilistic Planning.
S. Saisubramanian and S. Zilberstein. ICML/IJCAI/AAMAS Workshop on Planning and Learning (PAL-18), Stockholm, Sweden, 2018. [abs] [bib] [pdf]
Meta-Level Control of Anytime Algorithms with Online Performance Prediction.
J. Svegliato, K. Wray, and S. Zilberstein. Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI), Stockholm, Sweden, 2018. [abs] [bib] [pdf]
Belief-Space Planning for Automated Malware Defense.
J. Svegliato, S. Witty, A. Houmansadr, and S. Zilberstein. IJCAI-ECAI Workshop on AI for Internet of Things, Stockholm, Sweden, 2018. [abs] [bib] [pdf]
Adaptive Metareasoning for Bounded Rational Agents.
J. Svegliato and S. Zilberstein. IJCAI-ECAI Workshop on Architectures and Evaluation for Generality, Autonomy and Progress in AI (AEGAP), Stockholm, Sweden, 2018. [abs] [bib] [pdf]
Effective Cues for Accelerating Young Drivers' Time to Transfer Control Following a Period of Conditional Automation.
T.J. Wright, R. Agrawal, S. Samuel, Y. Wang, S. Zilberstein, and D.L. Fisher. Accident Analysis and Prevention, 116:14-20, 2018. [abs] [bib] [pdf]

2017[ top ]

Integration of Planning with Recognition for Responsive Interaction Using Classical Planners.
R.G. Freedman and S. Zilberstein. Proceedings of the Thirty-First Conference on Artificial Intelligence (AAAI), 4581-4588, San Francisco, California, 2017. [abs] [bib] [pdf]
Fast SSP Solvers Using Short-Sighted Labeling.
L. Pineda, K.H. Wray, and S. Zilberstein. Proceedings of the Thirty-First Conference on Artificial Intelligence (AAAI), 3629-3635, San Francisco, California, 2017. [abs] [bib] [pdf]
Robust Optimization for Tree-Structured Stochastic Network Design.
X. Wu, A. Kumar, D. Sheldon, and S. Zilberstein. Proceedings of the Thirty-First Conference on Artificial Intelligence (AAAI), 4545-4551, San Francisco, California, 2017. (Best Paper Award, Computational Sustainability Track) [abs] [bib] [pdf]
Generalizing the Role of Determinization in Probabilistic Planning.
L. Pineda and S. Zilberstein. Technical Report 2017-06, College of Information and Computer Sciences, University of Massachusetts Amherst, 2017. [abs] [bib] [pdf]
Approximating Reachable Belief Points in POMDPs with Applications to Robotic Navigation and Localization.
K.H. Wray and S. Zilberstein. ICAPS Workshop on Planning and Robotics (PlanRob), Pittsburgh, Pennsylvania, 2017. [abs] [bib] [pdf]
Equi-Reward Utility Maximizing Design in Stochastic Environments.
S. Keren, L. Pineda, A. Gal, E. Karpas, and S. Zilberstein. ICAPS Workshop on Heuristics and Search for Domain-independent Planning (HSDIP), Pittsburgh, Pennsylvania, 2017. [abs] [bib] [pdf]
Optimizing Electric Vehicle Charging Through Determinization.
S. Saisubramanian, S. Zilberstein, and P. Shenoy. ICAPS Workshop on Scheduling and Planning Applications (SPARK), Pittsburgh, Pennsylvania, 2017. [abs] [bib] [pdf]
A PDDL Representation for Contradance Composition.
R.G. Freedman and S. Zilberstein. ICAPS Workshop on Knowledge Engineering for Planning and Scheduling (KEPS), Pittsburgh, Pennsylvania, 2017. [abs] [bib] [pdf]
Equi-Reward Utility Maximizing Design in Stochastic Environments.
S. Keren, L. Pineda, A. Gal, E. Karpas, and S. Zilberstein. Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI), Melbourne, Australia, 2017. [abs] [bib] [pdf]
Online Decision-Making for Scalable Autonomous Systems.
K.H. Wray, S.J. Witwicki, and S. Zilberstein. Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI), Melbourne, Australia, 2017. [abs] [bib] [pdf]
Multi-Agent Planning with Baseline Regret Minimization.
F. Wu, S. Zilberstein, and X. Chen. Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI), Melbourne, Australia, 2017. [abs] [bib] [pdf]
Toward Effective Soft Robot Control via Reinforcement Learning.
H. Zhang, R. Cao, S. Zilberstein, F. Wu, and X. Chen. Proceedings of the International Conference on Intelligent Robotics and Applications (ICIRA), 173-184, Wuhan, China, 2017. [abs] [bib] [pdf]
Approximating Reachable Belief Points in POMDPs.
K.H. Wray and S. Zilberstein. Proceedings of the Thirtieth International Conference on Intelligent Robots and Systems (IROS),117-122, Vancouver, BC, Canada, 2017. [abs] [bib] [pdf]
The Effects of Alert Cue Specificity on Situation Awareness in Transfers of Control in Level 3 Automation.
T.J. Wright, R. Agrawal, S. Samuel, Y. Wang, S. Zilberstein, and D.L. Fisher. Journal of the Transportation Research Board, 2017. [abs] [bib] [pdf]
The Effects of a Change in Environment on the Minimum Time to Situation Awareness in Transfer of Control Scenarios.
R. Agrawal, T.J. Wright, S. Samuel, S. Zilberstein, and D.L. Fisher. Journal of the Transportation Research Board, 2017. [abs] [bib] [pdf]

2016[ top ]

A POMDP Formulation of Proactive Learning.
K.H. Wray and S. Zilberstein. Proceedings of the Thirtieth Conference on Artificial Intelligence (AAAI), 3202-3208, Phoenix, Arizona, 2016. [abs] [bib] [pdf]
Optimizing Resilience in Large Scale Networks.
X. Wu, D. Sheldon, and S. Zilberstein. Proceedings of the Thirtieth Conference on Artificial Intelligence (AAAI), 3922-3928, Phoenix, Arizona, 2016. [abs] [bib] [pdf]
Minimum Time to Situation Awareness in Scenarios Involving Transfer of Control from the Automation.
S. Samuel, A. Borowsky, S. Zilberstein, and D.L. Fisher. Proceedings of the 95th Annual Meeting of the Transportation Research Board (TRB), Washington, D.C., 2016. [abs] [bib] [pdf]
Hierarchical Approach to Transfer of Control in Semi-Autonomous Systems.
K.H. Wray, L. Pineda, and S. Zilberstein. Proceedings of the Fifteenth International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 1285-1286, Singapore, 2016. [abs] [bib] [pdf]
Dual Formulations for Optimizing Dec-POMDP Controllers.
A. Kumar, H. Mostafa, and S. Zilberstein. Proceedings of the Twenty-Sixth International Conference on Automated Planning and Scheduling (ICAPS), 202-210, London, UK, 2016. [abs] [bib] [pdf]
Hierarchical Approach to Transfer of Control in Semi-Autonomous Systems.
K.H. Wray, L. Pineda, and S. Zilberstein. Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence (IJCAI), 517-523, New York, NY, 2016. [abs] [bib] [pdf]
Fast SSP Solvers Using Short-Sighted Labeling.
L. Pineda, K.H. Wray, and S. Zilberstein. IJCAI Workshop on Goal Reasoning, New York, NY, 2016. [abs] [bib] [pdf]
Using Metadata to Automate Interpretations of Unsupervised Learning-Derived Clusters.
R.G. Freedman and S. Zilberstein. IJCAI Workshop on Human is More Than a Labeler, New York, NY, 2016. [abs] [bib] [pdf]
Experienced Drivers are Quicker to Achieve Situation Awareness within a Level 3 Autonomous Environment.
T.J. Wright, S. Samuel, A. Borowsky, S. Zilberstein, D.L. Fisher. Proceedings of the Human Factors and Ergonomics Society Annual Meeting (HFES), Washington, D.C., 2016. [abs] [bib] [pdf]
Log-Space Harmonic Function Path Planning.
K.H. Wray, D. Ruiken, R.A. Grupen, and S. Zilberstein. Proceedings of the Twenty-Ninth International Conference on Intelligent Robots and Systems (IROS), Daejeon, Korea, 2016. [abs] [bib] [pdf]
Safety in AI-HRI: Challenges Complementing User Experience Quality.
R.G. Freedman and S. Zilberstein. AAAI Fall Symposium on Artificial Intelligence for Human-Robot Interaction, Arlington, VA, 2016. [abs] [bib] [pdf]

2015[ top ]

Proceedings of the Twenty-Fifth International Conference on Automated Planning and Scheduling.
R. Brafman, C. Domshlak, P. Haslum, and S. Zilberstein (Eds). ICAPS, Jerusalem, Israel, June 7-11, 2015. [contents]
Probabilistic Inference Techniques for Scalable Multiagent Decision Making.
A. Kumar, S. Zilberstein, and M. Toussaint. Journal of Artificial Intelligence Research, 53:223-270, 2015. [abs] [bib] [pdf]
Multi-Objective MDPs with Conditional Lexicographic Reward Preferences.
K.H. Wray, S. Zilberstein, and A.I. Mouaddib. Proceedings of the Twenty-Ninth Conference on Artificial Intelligence (AAAI), 3418-3424, Austin, Texas, 2015. [abs] [bib] [pdf]
Building Strong Semi-Autonomous Systems.
S. Zilberstein. Proceedings of the Twenty-Ninth Conference on Artificial Intelligence (AAAI), 4088-4092, Austin, Texas, 2015. [abs] [bib] [pdf]
Tractability of Planning with Loops.
S. Srivastava, S. Zilberstein, A. Gupta, P. Abbeel, and S.J. Russell. Proceedings of the Twenty-Ninth Conference on Artificial Intelligence (AAAI), 3393-3401, Austin, Texas, 2015. [abs] [bib] [pdf]
Learning Therapy Strategies from Demonstration Using Latent Dirichlet Allocation.
H. Jung, R.G. Freedman, T. Foster, Y. Choe, S. Zilberstein, and R.A. Grupen. Proceedings of the Twentieth ACM Conference on Intelligent User Interfaces (IUI), 432-436, Atlanta, Georgia, 2015. [abs] [bib] [pdf]
History-Based Controller Design and Optimization for Partially Observable MDPs.
A. Kumar and S. Zilberstein. Proceedings of the Twenty-Fifth International Conference on Automated Planning and Scheduling (ICAPS), 156-164, Jerusalem, Israel, 2015. [abs] [bib] [pdf]
Handling Advice in MDPs for Semi-Autonomous Systems.
A.I. Mouaddib, L. Jeanpierre, and S. Zilberstein. ICAPS Workshop on Planning and Robotics (PlanRob), Jerusalem, Israel, 2015. [abs] [bib] [pdf]
Multi-Objective POMDPs with Lexicographic Reward Preferences.
K.H. Wray and S. Zilberstein. Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence (IJCAI), 1719-1725, Buenos Aires, Argentina, 2015. [abs] [bib] [pdf]
A Fast Combinatorial Algorithm for Optimizing the Spread of Cascades.
X. Wu, D. Sheldon, and S. Zilberstein. Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence (IJCAI), 2655-2661, Buenos Aires, Argentina, 2015. [abs] [bib] [pdf]
Adaptive Therapy Strategies: Efficacy and Learning Framework.
H. Jung, R.G. Freedman, T. Takahashi, J. Wong, S. Zilberstein, R. Grupen, and Y. Choe. Proceedings of the IEEE/RAS-EMBS International Conference on Rehabilitation Robotics (ICORR), Singapore, 2015. [abs] [bib] [pdf]
Automated Interpretations of Unsupervised Learning-Derived Clusters for Activity Recognition.
R.G. Freedman and S. Zilberstein. Ro-Man Workshop on Learning for Human-Robot Collaboration, Kobe, Japan, 2015. [abs] [bib] [pdf]
Continual Planning for Search and Rescue Robots.
L. Pineda, T. Takahashi, H. Jung, S. Zilberstein, and R. Grupen. Proceedings of the IEEE-RAS Fifteenth International Conference on Humanoid Robots (Humanoids), 243-248, Seoul, Korea, 2015. [abs] [bib] [pdf]
Temporal and Object Relations in Unsupervised Plan and Activity Recognition.
R.G. Freedman, H. Jung, and S. Zilberstein. AAAI Fall Symposium on Artificial Intelligence and Human-Robot Interaction (AI-HRI), Arlington, VA, 2015. [abs] [bib] [pdf]
Revisiting Multi-Objective MDPs with Relaxed Lexicographic Preferences.
L. Pineda, K.H. Wray, and S. Zilberstein. AAAI Fall Symposium on Sequential Decision Making for Intelligent Agents (SDMIA), Arlington, VA, 2015. [abs] [bib] [pdf]
A Parallel Point-Based POMDP Algorithm Leveraging GPUs.
K.H. Wray and S. Zilberstein. AAAI Fall Symposium on Sequential Decision Making for Intelligent Agents (SDMIA), Arlington, VA, 2015. [abs] [bib] [pdf]
Efficient Algorithms to Optimize Diffusion Processes under the Independent Cascade Model.
X. Wu, D. Sheldon, and S. Zilberstein. NIPS Workshop on Networks in the Social and Information Sciences, Montreal, Quebec, Canada, 2015. [abs] [bib] [pdf]

2014[ top ]

Decentralized Multi-Agent Reinforcement Learning in Average-Reward Dynamic DCOPs (Extended Abstract).
D.T. Nguyen, W. Yeoh, H.C. Lau, S. Zilberstein, and C. Zhang. Proceedings of the Thirteenth International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 1341-1342, Paris, France, 2014. [abs] [bib] [pdf]
Plan and Activity Recognition from a Topic Modeling Perspective.
R.G. Freedman, H. Jung, and S. Zilberstein. Proceedings of the Twenty-Fourth International Conference on Automated Planning and Scheduling (ICAPS), 360-364, Portsmouth, New Hampshire, 2014. [abs] [bib] [pdf]
Planning Under Uncertainty Using Reduced Models: Revisiting Determinization.
L. Pineda and S. Zilberstein. Proceedings of the Twenty-Fourth International Conference on Automated Planning and Scheduling (ICAPS), 217-225, Portsmouth, New Hampshire, 2014. [abs] [bib] [pdf]
Decentralized Multi-Agent Reinforcement Learning in Average-Reward Dynamic DCOPs.
D.T. Nguyen, W. Yeoh, H.C. Lau, S. Zilberstein, and C. Zhang. Proceedings of the Twenty-Eighth Conference on Artificial Intelligence (AAAI), 1447-1455, Quebec City, Canada 2014. [abs] [bib] [pdf]
Rounded Dynamic Programming for Tree-Structured Stochastic Network Design.
X. Wu, D. Sheldon, and S. Zilberstein. Proceedings of the Twenty-Eighth Conference on Artificial Intelligence (AAAI), 479-485, Quebec City, Canada 2014. [abs] [bib] [pdf]
Stochastic Network Design in Bidirected Trees.
X. Wu, D. Sheldon, and S. Zilberstein. Proceedings of the Twenty-Eighth Neural Information Processing Systems Conference (NIPS), 882-890, Montreal, Canada, 2014. [abs] [bib] [pdf]
Realtime Concurrent Planning and Plan Execution in Stochastic Domains.
L. Pineda and S. Zilberstein. Technical Report 2014-21, School of Computer Science, University of Massachusetts Amherst, 2014. [abs] [bib] [pdf]

2013[ top ]

Qualitative Planning under Partial Observability in Multi-Agent Domains.
R.I. Brafman, G. Shani, and S. Zilberstein. Proceedings of the Twenty-Seventh Conference on Artificial Intelligence (AAAI), 130-137, Bellevue, Washington, 2013. [abs] [bib] [pdf]
Fault-Tolerant Planning under Uncertainty.
L. Pineda, Y. Lu, S. Zilberstein, and C.V. Goldman. Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence (IJCAI), 2350-2356, Beijing, China, 2013. [abs] [bib] [pdf]
Monte-Carlo Expectation Maximization for Decentralized POMDPs.
F. Wu, S. Zilberstein, and N.R. Jennings. Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence (IJCAI), 397-403, Beijing, China, 2013. [abs] [bib] [pdf]
Parameter Learning for Latent Network Diffusion.
X. Wu, A. Kumar, D. Sheldon, and S. Zilberstein. Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence (IJCAI), 2923-2930, Beijing, China, 2013. [abs] [bib] [pdf]
Automated Generation of Interaction Graphs for Value-Factored Dec-POMDPs.
W. Yeoh, A. Kumar, and S. Zilberstein. Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence (IJCAI), 411-417, Beijing, China, 2013. [abs] [bib] [pdf]
Stochastic Network Design for River Networks.
X. Wu, D. Sheldon, and S. Zilberstein. NIPS Workshop on Machine Learning for Sustainability, Lake Tahoe, Nevada, 2013. [abs] [bib] [pdf]
Multiagent Planning, Control, and Execution.
E. Durfee and S. Zilberstein. In G. Weiss (Ed.), Multiagent Systems, Second Edition, 485-546, MIT Press, 2013. [abs] [bib] [pdf]

2012[ top ]

Applicability Conditions for Plans with Loops: Computability Results and Algorithms.
S. Srivastava, N. Immerman, and S. Zilberstein. Artificial Intelligence, 191:1-19, 2012. [abs] [bib] [pdf]
Message-Passing Algorithms for MAP Estimation Using DC Programming.
A. Kumar, S. Zilberstein, and M. Toussaint. Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics (AISTATS), 656-664, 2012. [abs] [bib] [pdf]
Lagrangian Relaxation Techniques for Scalable Spatial Conservation Planning.
A. Kumar, X. Wu, and S. Zilberstein. Proceedings of the Twenty-Sixth Conference on Artificial Intelligence (AAAI), 309-315, Toronto, Canada, 2012. [abs] [bib] [pdf]
Learning Feature-Based Heuristic Functions.
M. Petrik and S. Zilberstein. In Y. Hamadi, E. Monfroy, and F. Saubion (Eds.), Autonomous Search, 269-305, Springer, 2012. [abs] [bib] [pdf]

2011[ top ]

A New Representation and Associated Algorithms for Generalized Planning.
S. Srivastava, N. Immerman, and S. Zilberstein. Artificial Intelligence, 175(2):615-647, 2011. [abs] [bib] [pdf]
Online Planning for Multi-Agent Systems with Bounded Communication.
F. Wu, S. Zilberstein, and X. Chen. Artificial Intelligence, 175(2):487-511, 2011. [abs] [bib] [pdf]
Robust Approximate Bilinear Programming for Value Function Approximation.
M. Petrik and S. Zilberstein. Journal of Machine Learning Research, 12:3027-3063, 2011. [abs] [bib] [pdf]
Decentralized Monitoring of Anytime Decision Making.
A. Carlin and S. Zilberstein. Proceedings of the Tenth International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 157-164, Taipei, Taiwan, 2011. [abs] [bib] [pdf]
Message Passing Algorithms for Large Structured Decentralized POMDPs.
A. Kumar and S. Zilberstein. Proceedings of the Tenth International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 1087-1088, Taipei, Taiwan, 2011. [abs] [bib] [pdf]
Directed Search for Generalized Plans Using Classical Planners.
S. Srivastava, N. Immerman, S. Zilberstein, and T. Zhang. Proceedings of the Twenty-First International Conference on Automated Planning and Scheduling (ICAPS), 226-233, Freiburg, Germany, 2011. [abs] [bib] [pdf]
Message-Passing Algorithms for Quadratic Programming Formulations of MAP Estimation.
A. Kumar and S. Zilberstein. Proceedings of the Twenty-Seventh Conference on Uncertainty in Artificial Intelligence (UAI), 428-435, Barcelona, Spain, 2011. [abs] [bib] [pdf]
Scalable Multiagent Planning Using Probabilistic Inference.
A. Kumar, S. Zilberstein, and M. Toussaint. Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence (IJCAI), 2140-2146, Barcelona, Spain, 2011. [abs] [bib] [pdf]
Online Planning for Ad Hoc Autonomous Agent Teams.
F. Wu, S. Zilberstein, and X. Chen. Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence (IJCAI), 439-445, Barcelona, Spain, 2011. [abs] [bib] [pdf]
On Message-Passing MAP Estimation in Graphical Models and DCOPs.
A. Kumar, W. Yeoh, and S. Zilberstein. Proceedings of the Thirteenth International Workshop on Distributed Constraint Reasoning (DCR), 57-70, Barcelona, Spain, 2011. [abs] [bib] [pdf]
Linear Dynamic Programs for Resource Management.
M. Petrik and S. Zilberstein. Proceedings of the Twenty-Fifth Conference on Artificial Intelligence (AAAI), 1377-1383, San Francisco, California, 2011. [abs] [bib] [pdf]
Qualitative Numeric Planning.
S. Srivastava, S. Zilberstein, N. Immerman, and H. Geffner. Proceedings of the Twenty-Fifth Conference on Artificial Intelligence (AAAI), 1010-1016, San Francisco, California, 2011. [abs] [bib] [pdf]
Termination and Correctness Analysis of Cyclic Control.
S. Srivastava, N. Immerman, and S. Zilberstein. Proceedings of the Twenty-Fifth Conference on Artificial Intelligence (AAAI Nectar Track), 1567-1570, San Francisco, California, 2011. [abs] [bib] [pdf]
Influence Diagrams with Memory States: Representation and Algorithms.
X. Wu, A. Kumar, and S. Zilberstein. Proceedings of the Second International Conference on Algorithmic Decision Theory (ADT), Rutgers University, 2011. [abs] [bib] [pdf]
Metareasoning and Bounded Rationality.
S. Zilberstein. In M. Cox and A. Raja (Eds.), Metareasoning: Thinking about Thinking, 27-40, MIT Press, 2011. [abs] [bib] [pdf]
Bounded Rationality in Multiagent Systems Using Decentralized Metareasoning.
A. Carlin and S. Zilberstein. In T. Guy, M. Karny, and D. Wolpert (Eds.), Decision Making with Imperfect Decision Makers, 1-28, Springer, 2011. [abs] [bib] [pdf]

2010[ top ]

Optimizing Fixed-Size Stochastic Controllers for POMDPs and Decentralized POMDPs.
C. Amato, D.S. Bernstein, and S. Zilberstein. Autonomous Agents and Multi-Agent Systems, 21(3):293-320, 2010. [abs] [bib] [pdf]
Point-Based Backup for Decentralized POMDPs: Complexity and New Algorithms.
A. Kumar and S. Zilberstein. Proceedings of the Ninth International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 1315-1322, Toronto, Canada, 2010. [abs] [bib] [pdf]
Merging Example Plans into Generalized Plans for Non-deterministic Environments.
S. Srivastava, N. Immerman, and S. Zilberstein. Proceedings of the Ninth International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 1341-1348, Toronto, Canada, 2010. [abs] [bib] [pdf]
Point-Based Policy Generation for Decentralized POMDPs.
F. Wu, S. Zilberstein, and X. Chen. Proceedings of the Ninth International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 1307-1314, Toronto, Canada, 2010. [abs] [bib] [pdf]
Computing Applicability Conditions for Plans with Loops.
S. Srivastava, N. Immerman, and S. Zilberstein. Proceedings of the Twentieth International Conference on Automated Planning and Scheduling (ICAPS), 161-168, Toronto, Canada, 2010. (Best Paper Award) [abs] [bib] [pdf]
Feature Selection Using Regularization in Approximate Linear Programs for Markov Decision Processes.
M. Petrik, G. Taylor, R. Parr, and S. Zilberstein. Proceedings of the Twenty-Seventh International Conference on Machine Learning (ICML), Haifa, Israel, 2010. [abs] [bib] [pdf]
Anytime Planning for Decentralized POMDPs using Expectation Maximization.
A. Kumar and S. Zilberstein. Proceedings of the Twenty-Sixth Conference on Uncertainty in Artificial Intelligence (UAI), 294-301, Catalina Island, California, 2010. [abs] [bib] [pdf]
Rollout Sampling Policy Iteration for Decentralized POMDPs.
F. Wu, S. Zilberstein, and X. Chen. Proceedings of the Twenty-Sixth Conference on Uncertainty in Artificial Intelligence (UAI), 666-673, Catalina Island, California, 2010. [abs] [bib] [pdf]
Finite-State Controllers Based on Mealy Machines for Centralized and Decentralized POMDPs.
C. Amato, B. Bonet, and S. Zilberstein. Proceedings of the Twenty-Fourth Conference on Artificial Intelligence (AAAI), 1052-1058, Atlanta, Georgia, 2010. [abs] [bib] [pdf]
Trial-Based Dynamic Programming for Multi-Agent Planning.
F. Wu, S. Zilberstein, and X. Chen. Proceedings of the Twenty-Fourth Conference on Artificial Intelligence (AAAI), 908-914, Atlanta, Georgia, 2010. [abs] [bib] [pdf]
MAP Estimation for Graphical Models by Likelihood Maximization.
A. Kumar and S. Zilberstein. Proceedings of the Twenty-Fourth Neural Information Processing Systems Conference (NIPS), 1180-1188, Vancouver, British Columbia, 2010. [abs] [bib] [pdf]

2009[ top ]

Policy Iteration for Decentralized Control of Markov Decision Processes.
D.S. Bernstein, C. Amato, E.A. Hansen, and S. Zilberstein. Journal of Artificial Intelligence Research, 34:89-132, 2009. [abs] [bib] [pdf]
A Bilinear Programming Approach for Multiagent Planning.
M. Petrik and S. Zilberstein. Journal of Artificial Intelligence Research, 35:235-274, 2009. [abs] [bib] [pdf]
Analyzing Myopic Approaches for Multi-Agent Communications.
R. Becker, A. Carlin, V. Lesser, and S. Zilberstein. Computational Intelligence, 25(1):31-50, 2009. [abs] [bib] [pdf]
Achieving Goals in Decentralized POMDPs.
C. Amato and S. Zilberstein. Proceedings of the Eighth International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 593-600, Budapest, Hungary, 2009. [abs] [bib] [pdf]
Constraint-Based Dynamic Programming for Decentralized POMDPs with Structured Interactions.
A. Kumar and S. Zilberstein. Proceedings of the Eighth International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 561-568, Budapest, Hungary, 2009. [abs] [bib] [pdf]
Value of Communication In Decentralized POMDPs.
A. Carlin and S. Zilberstein. AAMAS Workshop on Multi-Agent Sequential Decision Making in Uncertain Domains (MSDM), Budapest, Hungary, 2009. [abs] [bib] [pdf]
Dynamic Programming Approximations for Partially Observable Stochastic Games.
A. Kumar and S. Zilberstein. Proceedings of the Twenty-Second International FLAIRS Conference, 547-552, Sanibel Island, Florida, 2009. [abs] [bib] [pdf]
Strategic Reasoning About Bundling in Swarming Systems.
D.S. Menasche, G. Neglia, D. Towsley, and S. Zilberstein. Proceedings of the International Conference on Game Theory for Networks (GameNets), 611-620, Istanbul, Turkey, 2009. [abs] [bib] [pdf]
Constraint Relaxation in Approximate Linear Programs.
M. Petrik and S. Zilberstein. Proceedings of the Twenty-Sixth International Conference on Machine Learning (ICML), 809-816, Montreal, Canada, 2009. [abs] [bib] [pdf]
Event-Detecting Multi-Agent MDPs: Complexity and Constant-Factor Approximation.
A. Kumar and S. Zilberstein. Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence (IJCAI), 201-207, Pasadena, California, 2009. [abs] [bib] [pdf]
Abstract Planning with Unknown Object Quantities and Properties.
S. Srivastava, N. Immerman, and S. Zilberstein. Proceedings of the Eighth Symposium on Abstraction, Reformulation and Approximation (SARA), 143-150, Lake Arrowhead, California, 2009. [abs] [bib] [pdf]
Incremental Policy Generation for Finite-Horizon DEC-POMDPs.
C. Amato, J.S. Dibangoye, and S. Zilberstein. Proceedings of the International Conference on Automated Planning and Scheduling (ICAPS), 2-9, Thessaloniki, Greece, 2009. [abs] [bib] [pdf]
Multi-Agent Online Planning with Communication.
F. Wu, S. Zilberstein, and X. Chen. Proceedings of the International Conference on Automated Planning and Scheduling (ICAPS), 321-329, Thessaloniki, Greece, 2009. [abs] [bib] [pdf]
Challenges in Finding Generalized Plans.
S. Srivastava, N. Immerman, and S. Zilberstein. ICAPS Workshop on Generalized Planning: Macros, Loops, Domain Control, Thessaloniki, Greece, 2009. [abs] [bib] [pdf]
Finding Plans with Branches, Loops and Preconditions.
S. Srivastava, N. Immerman, and S. Zilberstein. ICAPS Workshop on Verification and Validation of Planning and Scheduling Systems, Thessaloniki, Greece, 2009. [abs] [bib] [pdf]
Myopic and Non-Myopic Communication Under Partial Observability.
A. Carlin and S. Zilberstein. Proceedings of Intelligent Agent Technology (IAT), 331-338, Milan, Italy, 2009. [abs] [bib] [pdf]
Complexity of Decentralized Control: Special Cases.
M. Allen and S. Zilberstein. Proceedings of the Twenty-Third Neural Information Processing Systems Conference (NIPS), 19-27, Vancouver, British Columbia, December 2009. [abs] [bib] [pdf]
Robust Value Function Approximation Using Bilinear Programming.
M. Petrik and S. Zilberstein. Proceedings of the Twenty-Third Neural Information Processing Systems Conference (NIPS), 1446-1454, Vancouver, British Columbia, December 2009. [abs] [bib] [pdf]

2008[ top ]

Communication-Based Decomposition Mechanisms for Decentralized MDPs.
C.V. Goldman and S. Zilberstein. Journal of Artificial Intelligence Research, 32:169-202, 2008. [abs] [bib] [pdf]
Formal Models and Algorithms for Decentralized Decision Making under Uncertainty.
S. Seuken and S. Zilberstein. Autonomous Agents and Multi-Agent Systems, 17(2):190-250, October, 2008. [abs] [bib] [pdf]
A Successive Approximation Algorithm for Coordination Problems.
M. Petrik and S. Zilberstein. Proceedings of the Tenth International Symposium on Artificial Intelligence and Mathematics (ISAIM), Ft. Lauderdale, Florida, 2008. [abs] [bib] [pdf]
Using Abstraction for Generalized Planning.
S. Srivastava, N. Immerman, and S. Zilberstein. Proceedings of the Tenth International Symposium on Artificial Intelligence and Mathematics (ISAIM), Ft. Lauderdale, Florida, 2008. [abs] [bib] [pdf]
Value-Based Observation Compression for DEC-POMDPs.
A. Carlin and S. Zilberstein. Proceedings of the Seventh International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 501-508, Estoril, Portugal, 2008. [abs] [bib] [pdf]
Heuristic Policy Iteration for Infinite-Horizon Decentralized POMDPs.
C. Amato and S. Zilberstein. AAMAS Workshop on Multi-Agent Sequential Decision Making in Uncertain Domains (MSDM), 1-15, Estoril, Portugal, 2008. [abs] [bib] [pdf]
Observation Compression in DEC-POMDP Policy Trees.
A. Carlin and S. Zilberstein. AAMAS Workshop on Multi-Agent Sequential Decision Making in Uncertain Domains (MSDM), 31-45, Estoril, Portugal, 2008. [abs] [bib] [pdf]
Learning Generalized Plans Using Abstract Counting.
S. Srivastava, N. Immerman, and S. Zilberstein. Proceedings of the Twenty-Third Conference on Artificial Intelligence (AAAI), 991-997, Chicago, Illinois, 2008. [abs] [bib] [pdf]
Metareasoning and Bounded Rationality.
S. Zilberstein. AAAI Workshop on Metareasoning: Thinking about Thinking, Chicago, Illinois, 2008. [abs] [bib] [pdf]
Optimizing Fixed-Size Stochastic Controllers for POMDPs.
C. Amato, D.S. Bernstein, and S. Zilberstein. AAAI Workshop on Advancements in POMDP Solvers, Chicago, Illinois, 2008. [abs] [bib] [pdf]
POMDP and DEC-POMDP Point-Based Observation Aggregation.
A. Carlin and S. Zilberstein. AAAI Workshop on Advancements in POMDP Solvers, Chicago, Illinois, 2008. [abs] [bib] [pdf]
Learning Heuristic Functions Through Approximate Linear Programming.
M. Petrik and S. Zilberstein. Proceedings of the International Conference on Automated Planning and Scheduling (ICAPS), 248-255, Sydney, Australia, 2008. [abs] [bib] [pdf]
What's Worth Memorizing: Attribute-based Planning for DEC-POMDPs.
C. Amato and S. Zilberstein. ICAPS Workshop on Multiagent Planning, Sydney, Australia, 2008. [abs] [bib] [pdf]
Interaction Structure and Dimensionality in Decentralized Problem Solving
M. Allen, M. Petrik, and S. Zilberstein. Technical Report 08-11, Computer Science Department, University of Massachusetts Amherst, 2008. [abs] [bib] [pdf]

2007[ top ]

Learning to Communicate in a Decentralized Environment.
C.V. Goldman, M. Allen, and S. Zilberstein. Autonomous Agents and Multi-Agent Systems, 15(1):47-90, 2007. [abs] [bib] [pdf]
Solving POMDPs Using Quadratically Constrained Linear Programs.
C. Amato, D.S. Bernstein, and S. Zilberstein. Proceedings of the Twentieth International Joint Conference on Artificial Intelligence (IJCAI), 2418-2424, Hyderabad, India, 2007. [abs] [bib] [pdf]
Web Page Clustering using Heuristic Search in the Web Graph.
R. Bekkerman, S. Zilberstein, and J. Allan. Proceedings of the Twentieth International Joint Conference on Artificial Intelligence (IJCAI), 2280-2285, Hyderabad, India, 2007. [abs] [bib] [pdf]
Average-Reward Decentralized Markov Decision Processes.
M. Petrik and S. Zilberstein. Proceedings of the Twentieth International Joint Conference on Artificial Intelligence (IJCAI), 1997-2002, Hyderabad, India, 2007. [abs] [bib] [pdf]
Memory-Bounded Dynamic Programming for DEC-POMDPs.
S. Seuken and S. Zilberstein. Proceedings of the Twentieth International Joint Conference on Artificial Intelligence (IJCAI), 2009-2015, Hyderabad, India, 2007. [abs] [bib] [pdf]
Bounded Dynamic Programming for Decetralized POMDPs.
C. Amato, A. Carlin, and S. Zilberstein. AAMAS Workshop on Multi-Agent Sequential Decision Making in Uncertain Domains (MSDM), Honolulu, Hawaii, May, 2007. [abs] [bib] [pdf]
Optimizing Memory-Bounded Controllers for Decentralized POMDPs.
C. Amato, D.S. Bernstein, and S. Zilberstein. Proceedings of the Twenty-Third Conference on Uncertainty in Artificial Intelligence (UAI), 1-8, Vancouver, British Columbia, 2007. [abs] [bib] [pdf]
Improved Memory-Bounded Dynamic Programming for Decentralized POMDPs.
S. Seuken and S. Zilberstein. Proceedings of the Twenty-Third Conference on Uncertainty in Artificial Intelligence (UAI), 344-351, Vancouver, British Columbia, 2007. [abs] [bib] [pdf]
Agent Influence as a Predictor of Difficulty for Decentralized Problem-Solving.
M. Allen and S. Zilberstein. Proceedings of the Twenty-Second Conference on Artificial Intelligence (AAAI), 688-693, Vancouver, British Columbia, 2007. [abs] [bib] [pdf]
Anytime Coordination Using Separable Bilinear Programs.
M. Petrik and S. Zilberstein. Proceedings of the Twenty-Second Conference on Artificial Intelligence (AAAI), 750-755, Vancouver, British Columbia, 2007. [abs] [bib] [pdf]
Using Abstraction for Generalized Planning.
S. Srivastava, N. Immerman, and S. Zilberstein. ICAPS Workshop on Artificial Intelligence Planning and Learning, Providence, Rhode Island, 2007. [abs] [bib] [pdf]

2006[ top ]

Learning Parallel Portfolios of Algorithms.
M. Petrik and S. Zilberstein. Annals of Mathematics and Artificial Intelligence, 48(1-2):85-106, 2006. [abs] [bib] [pdf]
Annals of Artificial Intelligence and Mathematics Special Issue.
Selected Papers from the Ninth International Symposium on Artificial Intelligence and Mathematics, S. Zilberstein (Ed.), Volume 47(3-4), 2006. [contents]
Solving POMDPs Using Quadratically Constrained Linear Programs.
C. Amato, D.S. Bernstein, and S. Zilberstein. Proceedings of the Ninth International Symposium on Artificial Intelligence and Mathematics (ISAIM), Ft. Lauderdale, Florida, 2006. [abs] [bib] [pdf]
Learning Static Parallel Portfolios of Algorithms.
M. Petrik and S. Zilberstein. Proceedings of the Ninth International Symposium on Artificial Intelligence and Mathematics (ISAIM), Ft. Lauderdale, Florida, 2006. [abs] [bib] [pdf]
Optimal Fixed-Size Controllers for Decentralized POMDPs.
C. Amato, D.S. Bernstein, and S. Zilberstein. AAMAS Workshop on Multi-Agent Sequential Decision Making in Uncertain Domains (MSDM), 61-71, Hakodate, Japan, May, 2006. [abs] [bib] [pdf]

2005[ top ]

Learning to Communicate in Decentralized Systems.
M. Allen, C.V. Goldman, and S. Zilberstein. Eighth Binennial Israeli Symposium on the Foundations of AI (BISFAI), Haifa, Israel, 2005. [abs] [bib] [pdf]
Efficient Maximization in Solving POMDPs.
Z. Feng and S. Zilberstein. Proceedings of the Twentieth National Conference on Artificial Intelligence (AAAI), 975-980, Pittsburgh, Pennsylvania, 2005. [abs] [bib] [pdf]
Generating Admissible Heuristics by Abstraction for Search in Stochastic Domains.
N. Beliaeva and S. Zilberstein. Proceedings of the Symposium on Abstraction, Reformulation, and Approximation (SARA), 14-29, Airth Castle, Scotland, 2005. [abs] [bib] [pdf]
MAA*: A Heuristic Search Algorithm for Solving Decentralized POMDPs.
D. Szer, F. Charpillet, and S. Zilberstein. Proceedings of the Twenty-First Conference on Uncertainty in Artificial Intelligence (UAI), 576-583, Edinburgh, Scotland, 2005. [abs] [bib] [pdf]
Language Learning in Multi-Agent Systems.
M. Allen, C.V. Goldman, and S. Zilberstein. Poster presented at the Nineteenth International Joint Conference on Artificial Intelligence (IJCAI), 1649-1650, Edinburgh, Scotland, 2005. [abs] [bib] [pdf]
Bounded Policy Iteration for Decentralized POMDPs.
D.S. Bernstein, E.A. Hansen, and S. Zilberstein. Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence (IJCAI), 1287-1292, Edinburgh, Scotland, 2005. [abs] [bib] [pdf]
Analyzing Myopic Approaches for Multi-Agent Communication.
R. Becker, V. Lesser, and S. Zilberstein. Proceedings of Intelligent Agent Technology (IAT), 550-557, Compiègne, France, 2005. (Best Paper Award) [abs] [bib] [pdf]
Learning Policies for Sequential Time and Cost Sensitive Classification.
A. Arnt and S. Zilberstein. KDD Workshop on Utility-Based Data Mining, Chicago, Illinois, 2005. [abs] [bib] [pdf]

2004[ top ]

Proceedings of the Fourteenth International Conference on Automated Planning and Scheduling.
S. Zilberstein, J. Koehler, and S. Koenig (Eds). ICAPS, Whistler, British Columbia, Canada, June 3-7, 2004. [contents]
Solving Transition-Independent Decentralized Markov Decision Processes.
R. Becker, S. Zilberstein, V. Lesser, and C.V. Goldman. Journal of Artificial Intelligence Research, 22:423-455, 2004. [abs] [bib] [pdf]
Decentralized Control of Cooperative Systems: Categorization and Complexity Analysis.
C.V. Goldman and S. Zilberstein. Journal of Artificial Intelligence Research, 22:143-174, 2004. [abs] [bib] [pdf]
Dynamic Composition of Information Retrieval Techniques.
A. Arnt, S. Zilberstein, J. Allan, and A.I. Mouaddib. Journal of Intelligent Information Systems, 23(1):67-97, 2004. [abs] [bib] [pdf]
Dynamic Programming for Decentralized POMDPs.
D.S. Bernstein, E.A. Hansen, S. Zilberstein, and C. Amato. AAAI Spring Symposium on Bridging the Multi-Agent and Multi-Robot Research Gap, Stanford, California, 2004. [abs] [bib] [pdf]
Automated Conversion and Simplification of Plan Representations.
M. Allen and S. Zilberstein. ICAPS Workshop on Connecting Planning Theory with Practice, Whistler, British Columbia, 2004. [abs] [bib] [pdf]
Decentralized Markov Decision Processes with Event-Driven Interactions.
R. Becker, S. Zilberstein, and V. Lesser. Proceedings of the Third International Joint Conference on Autonomous Agents and Multi Agent Systems (AAMAS), 302-309, New York City, 2004. [abs] [bib] [pdf]
Decentralized Language Learning Through Acting.
C.V. Goldman, M. Allen, and S. Zilberstein. Proceedings of the Third International Joint Conference on Autonomous Agents and Multi Agent Systems (AAMAS), 1006-1013, New York City, 2004. [abs] [bib] [pdf]
Dynamic Programming for Partially Observable Stochastic Games.
E.A. Hansen, D.S. Bernstein, and S. Zilberstein. Proceedings of the Nineteenth National Conference on Artificial Intelligence (AAAI), 709-715, San Jose, California, 2004. [abs] [bib] [pdf]
Region-Based Incremental Pruning for POMDPs.
Z. Feng and S. Zilberstein. Proceedings of the Twentieth Conference on Uncertainty in Artificial Intelligence (UAI), 146-153, Banff, Canada. 2004. [abs] [bib] [pdf]
Optimal Decisions with Continuous Actions.
L. Jeanpierre, S. Zilberstein, and F. Charpillet. Jurnées Nationales sur Processus Décisionnel de Markov et Intelligence Artificielle. [abs] [bib] [pdf]
Attribute Measurement Policies for Cost-Effective Classification.
A. Arnt and S. Zilberstein. SIAM/SDM Workshop on Data Mining in Resource Constrained Environments, Lake Buena Vista, Florida, 2004. [abs] [bib] [pdf]
Heuristic-Guided Counterexample Search in FLAVERS.
J. Tan, G.S. Avrunin, L.A. Clarke, S. Zilberstein, and S. Leue. Proceedings of ACM SIGSOFT FSE, 201-210, Newport Beach, California, 2004. [abs] [bib] [pdf]

2003[ top ]

Optimal Sequencing of Contract Algorithms.
S. Zilberstein, F. Charpillet, and P. Chassaing. Annals of Mathematics and Artificial Intelligence, 39(1-2):1-18, 2003. [abs] [bib] [pdf] [erratum]
Decision Making and Uncertainty Management in a 3D Reconstruction System.
M. Marengoni, A. Hanson, S. Zilberstein, and E. Riseman. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(7):852-858, 2003. [abs] [bib] [pdf]
Adaptive Peer Selection.
D.S. Bernstein, Z. Feng, B. Levine, and S. Zilberstein. Proceedings of the Second International Workshop on Peer-to-Peer Systems, 237-246, Berkeley, California, 2003. [abs] [bib] [pdf]
Transition-Independent Decentralized Markov Decision Processes.
R. Becker, S. Zilberstein, V. Lesser, and C.V. Goldman. Proceedings of the Second International Conference on Autonomous Agents and Multi Agent Systems (AAMAS), 41-48, Melbourne, Australia, 2003. (Best Paper Award) [abs] [bib] [pdf]
Optimizing Information Exchange in Cooperative Multi Agent Systems.
C.V. Goldman and S. Zilberstein. Proceedings of the Second International Conference on Autonomous Agents and Multi Agent Systems (AAMAS), 137-144, Melbourne, Australia, 2003. [abs] [bib] [pdf]
Mechanism Design for Communication in Cooperative Systems.
C.V. Goldman and S. Zilberstein. Fifth Workshop on Game Theoretic and Decision Theoretic Agents (GTDT), Melbourne, Australia, 2003. [abs] [bib] [pdf]
Automated Generation of Understandable Contingency Plans.
M. Horstmann and S. Zilberstein. ICAPS Workshop on Planning Under Uncertainty and Incomplete Information, Trento, Italy, 2003. [abs] [bib] [pdf]
Symbolic Generalization for On-line Planning.
Z. Feng, E.A. Hansen, and S. Zilberstein. Proceedings of the Nineteenth Conference on Uncertainty in Artificial Intelligence (UAI), 209-216, Acapulco, Mexico, 2003. [abs] [bib] [pdf]
Contract Algorithms and Robots on Rays: Unifying Two Scheduling Problems.
D.S. Bernstein, L. Finkelstein, and S. Zilberstein. Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence (IJCAI), 1211-1217, Acapulco, Mexico, 2003. [abs] [bib] [pdf]
Automated Generation of Understandable Contingency Plans.
M. Horstmann and S. Zilberstein. Poster presented at the Eighteenth International Joint Conference on Artificial Intelligence (IJCAI), 1518-1519, Acapulco, Mexico, 2003. [abs] [bib] [pdf]
Symbolic Real-Time Dynamic Programming.
Z. Feng, S. Zilberstein, and E.A. Hansen. IJCAI Workshop on Model Checking and Artificial Intelligence, Acapulco, Mexico, 2003. [abs] [bib] [pdf]
Learning to Perform Moderation in Online Forums.
A. Arnt and S. Zilberstein. Proceedings of Web Intelligence, 637-641, Acapulco, Mexico, 2003. [abs] [bib] [pdf]

2002[ top ]

The Complexity of Decentralized Control of Markov Decision Processes.
D.S. Bernstein, R. Givan, N. Immerman, and S. Zilberstein. Mathematics of Operations Research, 27(4):819-840, 2002. [abs] [bib] [pdf]
Scheduling Contract Algorithms on Multiple Processors
D.S. Bernstein, T.J. Perkins, S. Zilberstein, and L. Finkelstein. Proceedings of the Eighteenth National Conference on Artificial Intelligence (AAAI), 702-706, Edmonton, Alberta, Canada, 2002. [abs] [bib] [pdf]
Decision-Theoretic Control of Planetary Rovers
S. Zilberstein, R. Washington, D.S. Bernstein, and A.I. Mouaddib. In M. Beetz et al. (Eds.), Plan-Based Control of Robotic Agents, LNAI, No. 2466, 270-289, 2002. [abs] [bib] [pdf]

2001[ top ]

Artificial Intelligence Journal Special Issue on Computational Tradeoffs under Bounded Resources.
E. Horvitz and S. Zilberstein (Eds.), Volume 126(1-2), 2001. [contents]
Monitoring and Control of Anytime Algorithms: A Dynamic Programming Approach
E.A. Hansen and S. Zilberstein. Artificial Intelligence, 126(1-2):139-157, 2001. [abs] [bib] [pdf]
LAO*: A Heuristic Search Algorithm that Finds Solutions with Loops
E.A. Hansen and S. Zilberstein. Artificial Intelligence, 129(1-2):35-62, 2001. [abs] [bib] [pdf]
Adaptive Control of Acyclic Progressive Processing Task Structures
S. Cardon, A.I. Mouaddib, S. Zilberstein, and R. Washington. Proceedings of the Seventeenth International Joint Conference on Artificial Intelligence (IJCAI), 701-706, Seattle, Washington, 2001. [abs] [bib] [pdf]
Reinforcement Learning for Weakly-Coupled MDPs and an Application to Planetary Rover Control
D.S. Bernstein and S. Zilberstein. Proceedings of the Sixth European Conference on Planning (ECP), 373-378, Toledo, Spain, 2001. [abs] [bib] [pdf]
Communication Decisions in Multi-agent Cooperation: Model and Experiments
P. Xuan, V. Lesser, and S. Zilberstein. Proceedings of the Fifth International Conference on Autonomous Agents (AGENTS), 616-623, Montreal, Canada, 2001. [abs] [bib] [pdf]
Planetary Rover Control as a Markov Decision Process
D.S. Bernstein, S. Zilberstein, R. Washington, and J. Bresina. The Sixth International Symposium on Artificial Intelligence, Robotics and Automation in Space, Montreal, Canada, 2001. [abs] [bib] [pdf]

2000[ top ]

Optimal Scheduling of Progressive Processing Tasks
S. Zilberstein and A.I. Mouaddib. International Journal of Approximate Reasoning, 25(3):169-186, 2000. [abs] [bib] [pdf]
A Value-Driven System for Autonomous Information Gathering
J. Grass and S. Zilberstein. Journal of Intelligent Information Systems, 14(1):5-27, 2000. [abs] [bib] [pdf]
Dynamic Scheduling of Progressive Processing Plans
S. Zilberstein, A.I. Mouaddib, and A. Arnt. Proceedings of ECAI Workshop on New Results in Planning, Scheduling and Design, Berlin, Germany, August, 2000. [abs] [bib] [pdf]
The Complexity of Decentralized Control of Markov Decision Processes
D.S. Bernstein, S. Zilberstein, and N. Immerman. Proceedings of the Sixteenth Conference on Uncertainty in Artificial Intelligence (UAI), 32-37, Stanford, California, July, 2000. [abs] [bib] [pdf]
Communication in Multi-agent Markov Decision Processes
P. Xuan, V. Lesser, and S. Zilberstein. Proceedings of ICMAS Workshop on Game Theoretic and Decision Theoretic Agents, Boston, MA, July, 2000. [abs] [bib] [pdf]
Optimizing Resource Utilization in Planetary Rovers
S. Zilberstein and A.I. Mouaddib. Proceedings of the Second NASA International Workshop on Planning and Scheduling for Space, 163-168, San Francisco, California, 2000. [abs] [bib] [pdf]

1999[ top ]

Optimal Sequencing of Contract Algorithms
S. Zilberstein, F. Charpillet, and P. Chassaing. Bar-Ilan Symposium on the Foundation of Artificial Intelligence (BISFAI), Ramat Gan, Israel, 1999. [abs] [bib] [pdf]
A Heuristic Search Algorithm for Markov Decision Problems
E.A. Hansen and S. Zilberstein. Bar-Ilan Symposium on the Foundation of Artificial Intelligence (BISFAI), Ramat Gan, Israel, 1999. [abs] [bib] [pdf]
Real-Time Problem-Solving with Contract Algorithms
S. Zilberstein, F. Charpillet, and P. Chassaing. Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence (IJCAI), 1008-1015, Stockholm, Sweden, 1999. [abs] [bib] [pdf] [erratum]
Reactive Control of Dynamic Progressive Processing
S. Zilberstein and and A.I. Mouaddib. Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence (IJCAI), 1268-1273, Stockholm, Sweden, 1999. [abs] [bib] [pdf]
Control in a 3D Reconstruction System Using Selective Perception
M. Marengoni, A. Hanson, S. Zilberstein, and E. Riseman. Proceedings of the Seventh IEEE International Conference on Computer Vision (ICCV), 1229-1236, Kerkyra, Greece, 1999. [abs] [bib] [pdf]

1998[ top ]

Satisficing and Bounded Optimality
S. Zilberstein. AAAI Spring Symposium on Satisficing Models, Stanford, California, 1998. [abs] [bib] [pdf]
Heuristic Search in Cyclic AND/OR Graphs
E.A. Hansen and S. Zilberstein. Proceedings of the Fifteenth National Conference on Artificial Intelligence (AAAI), 412-418, Madison, Wisconsin, 1998. [abs] [bib] [pdf]
From HTML to Usable Data: Problems in Meaning and Credibility in the WWW
J. Grass and S. Zilberstein. AAAI Workshop on AI and Information Integration, Madison, Wisconsin, 1998. [abs] [bib] [pdf]
Optimal Scheduling of Dynamic Progressive Processing
A.I. Mouaddib and S. Zilberstein. Proceedings of the Thirteenth European Conference on Artificial Intelligence (ECAI), 499-503, Brighton, UK, 1998. (Best Paper Award) [abs] [bib] [pdf]
New Directions in Modeling and Control of Progressive Processing
A.I. Mouaddib, S. Zilberstein and Victor Danilchenko. ECAI Workshop on Monitoring and Control of Real-Time Intelligent Systems, Brighton, UK, 1998. [abs] [bib] [pdf]

1997[ top ]

Formalizing the Notion of "Satisficing"
S. Zilberstein. AAAI Spring Symposium on Qualitative Preferences in Deliberation and Practical Reasoning, Stanford, California, 1997. [abs] [bib] [pdf]
An Anytime Approach to Analyzing Software Systems
D. Rubenstein, L. Osterweil, and S. Zilberstein. Proceedings of the 10th International Florida Artificial Intelligence Research Symposium (FLAIRS), 386-391, Daytona Beach, Florida, 1997. [abs] [bib] [pdf]
Value-Driven Information Gathering
J. Grass and S. Zilberstein. AAAI Workshop on Building Resource-Bounded Reasoning Systems, Providence, Rhode Island, 1997. [abs] [bib] [pdf]
Handling Duration Uncertainty in Meta-Level Control of Progressive Processing
A.I. Mouaddib and S. Zilberstein. Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence (IJCAI), 1201-1207, Nagoya, Japan, 1997. [abs] [bib] [pdf]
Anytime Heuristic Search: First Results
E.A. Hansen, S. Zilberstein, and V.A. Danilchenko. Technical Report 97-50, Computer Science Department, University of Massachusetts Amherst, 1997. [abs] [bib] [pdf]

1996[ top ]

Optimal Composition of Real-Time Systems
S. Zilberstein and S.J. Russell. Artificial Intelligence, 82(1-2):181-213, 1996. [abs] [bib] [pdf]
Resource-Bounded Sensing and Planning in Autonomous Systems
S. Zilberstein. Autonomous Robots, 3:31-48, 1996. [abs] [bib] [pdf]
Using Anytime Algorithms in Intelligent Systems
S. Zilberstein. AI Magazine, 17(3):73-83, 1996. [abs] [bib] [pdf]
Anytime Algorithm Development Tools
J. Grass and S. Zilberstein. In M. Pittarelli (Ed.), SIGART Bulletin Special Issue on Anytime Algorithms and Deliberation Scheduling, 7(2):20-27, 1996. [abs] [bib] [pdf]
Monitoring Anytime Algorithms
E.A. Hansen and S. Zilberstein. In M. Pittarelli (Ed.), SIGART Bulletin Special Issue on Anytime Algorithms and Deliberation Scheduling, 7(2):28-33, 1996. [abs] [bib] [pdf]
Monitoring the Progress of Anytime Problem-Solving
E.A. Hansen and S. Zilberstein. Proceedings of the Thirteenth National Conference on Artificial Intelligence (AAAI), 1229-1234, Portland, Oregon, 1996. [abs] [bib] [pdf]
Reinforcement Learning for Mixed Open-loop and Closed-loop Control
E.A. Hansen, A.G. Barto, and S. Zilberstein. Proceedings of the Ninth Neural Information Processing Systems Conference (NIPS), 1026-1032, Denver, Colorado, 1996. [abs] [bib] [pdf]
Intelligent Information Gathering Using Decision Models
S. Zilberstein and V. Lesser. Technical Report 96-35, Computer Science Department, University of Massachusetts Amherst, 1996. [abs] [bib] [pdf]

1995[ top ]

On the Utility of Planning
S. Zilberstein. In M. Pollack (Ed.), SIGART Bulletin Special Issue on Evaluating Plans, Planners, and Planning Systems, 6(1):42-47, 1995. [abs] [bib] [pdf]
Models of Bounded Rationality
S. Zilberstein. AAAI Fall Symposium on Rational Agency, Cambridge, Massachusetts, 1995. [abs] [bib] [pdf]
Optimizing Decision Quality with Contract Algorithms
S. Zilberstein. Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence (IJCAI), 1576-1582, Montreal, Canada, 1995. [abs] [bib] [pdf]
Knowledge-Based Anytime Computation
A.I. Mouaddib and S. Zilberstein. Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence (IJCAI), 775-781, Montreal, Canada, 1995. [abs] [bib] [pdf]
Approximate Reasoning Using Anytime Algorithms
S. Zilberstein and S.J. Russell. In S. Natarajan (Ed.), Imprecise and Approximate Computation, Kluwer Academic Publishers, 1995. [abs] [bib] [pdf]

1994[ top ]

Teaching Graduate-level Artificial Intelligence
S. Zilberstein. AAAI Fall Symposium on Instruction of Introductory AI, New Orleans, Louisiana, 1994. [abs] [bib] [pdf]
Meta-level Control of Approximate Reasoning: A Decision Theoretic Approach
S. Zilberstein. Proceedings of the Eighth International Symposium on Methodologies for Intelligent Systems (ISMIS), 114-123, Charlotte, North Carolina, 1994. [abs] [bib] [pdf]

1993[ top ]

Anytime Sensing, Planning and Action: A Practical Model for Robot Control
S. Zilberstein and S.J. Russell. Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence (IJCAI), 1402-1407, Chambery, France, 1993. [abs] [bib] [pdf]
Operational Rationality through Compilation of Anytime Algorithms
S. Zilberstein. Ph.D. dissertation, Computer Science Division, University of California at Berkeley, 1993. [abs] [bib] [pdf]

1992[ top ]

Efficient Resource-Bounded Reasoning in AT-RALPH
S. Zilberstein and S.J. Russell. Proceedings of the First International Conference on AI Planning Systems (AIPS), 260-266, College Park, Maryland, 1992. [abs] [bib] [pdf]

1991[ top ]

Composing Real-Time Systems
S.J. Russell and S. Zilberstein. Proceedings of the Twelfth International Joint Conference on Artificial Intelligence (IJCAI), 212-217, Sydney, Australia, 1991. [abs] [bib] [pdf]

The publications on this website are provided for non-commercial research and education use. Not for reproduction, distribution or commercial use.

shlomo@cs.umass.edu