• Publications
  • Influence
The Complexity of Decentralized Control of Markov Decision Processes
This work considers decentralized control of Markov decision processes and gives complexity bounds on the worst-case running time for algorithms that find optimal solutions and describes generalizations that allow for decentralized control. Expand
LAO*: A heuristic search algorithm that finds solutions with loops
It is shown that LAO* can be used to solve Markov decision problems and that it shares the advantage heuristic search has over dynamic programming for other classes of problems. Expand
Dynamic Programming for Partially Observable Stochastic Games
An exact dynamic programming algorithm for partially observable stochastic games (POSGs) is developed and it is proved that when applied to finite-horizon POSGs, the algorithm iteratively eliminates very weakly dominated strategies without first forming a normal form representation of the game. Expand
Solving Transition Independent Decentralized Markov Decision Processes
This work presents a novel algorithm for solving a specific class of decentralized MDPs in which the agents' transitions are independent, and lays the foundation for further work in this area on both exact and approximate algorithms. Expand
Models of Bounded Rationality
Using Anytime Algorithms in Intelligent Systems
A wide range of existing solutions to the metalevel control problem are outlined and current work that is aimed at increasing the applicability of anytime computation is described. Expand
Decentralized Control of Cooperative Systems: Categorization and Complexity Analysis
This paper identifies classes of decentralized control problems whose complexity ranges between NEXP and P, and distinguishes between three ways in which agents can exchange information: indirect communication, direct communication and sharing state features that are not controlled by the agents. Expand
Optimizing information exchange in cooperative multi-agent systems
This paper develops a decision-theoretic solution to centralized control of a cooperative multi-agent system, treating both standard actions and communication as explicit choices that the decision maker must consider, and presents an analytical model to evaluate the trade-off between the cost of communication and the value of the information received. Expand
Formal models and algorithms for decentralized decision making under uncertainty
Five different formal frameworks, three different optimal algorithms, as well as a series of approximation techniques are analyzed to provide interesting insights into the structure of decentralized problems, the expressiveness of the various models, and the relative advantages and limitations of the different solution techniques. Expand
Operational Rationality through Compilation of Anytime Algorithms
An important result of this work is a general method by which an interruptible algorithm can be constructed once a contract algorithm is compiled and local compilation is proved to yield global optimality for a large set of program structures. Expand