AI Seminar

Toyota AI Lab Seminar

Piotr J. GmytrasiewiczInteractive Partially Observable Markov Decision ProcessesAssociate Professor, Computer Science, University of Illinois at Chicago

In our work we adopted the decision-theoretic principle of expected utility maximization as a paradigm for designing autonomous rational agents operating in multi-agent environments. Our approach differs from techniques based on game theory; we are not looking for equilibria, and we do not have to assume that the agents have arrived at the state of common knowledge. Instead, we endow an agent with a representation that captures the agent's knowledge about the environment and about the other agents, including its knowledge about their states of knowledge, which can include what they know about the other agents, and so on. This approach has been called the decision-theoretic approach to game theory. It avoids some of the drawbacks of game-theoretic equilibria that may be nonunique and do not capture off-equilibrium behaviors, but it does so at the cost of having to represent, process and continually update the nested state of agent's knowledge.

Piotr Gmytrasiewicz is an associate professor in the Computer Science Department at the University of Illinois at Chicago. His research interests concentrate on rational artificial agents, distributed artificial intelligence, uncertainty reasoning, automated decision-making, multi-agent coordination and intelligent communication, distributed optimization and control.

Prior to joining UIC he has been an associate professor in the Computer Science and Engineering Department at the University of Texas at Arlington, a visiting Assistant Professor in the Department of Computer Science at the University of California at Riverside, and a researcher at the Artificial Intelligence Laboratory at the Hebrew University of Jerusalem. He is currently a member of editorial Board of the Journal of Artificial Intelligence Research.

Sponsored by

AI Lab