In large extensive form games with imperfect information, Counterfactual Regret Minimization (CFR) is a popular, iterative algorithm for computing approximate Nash equilibria. Whi...
Richard G. Gibson, Marc Lanctot, Neil Burch, Duane...
Games are used to evaluate and advance Multiagent and Artificial Intelligence techniques. Most of these games are deterministic with perfect information (e.g. Chess and Checkers)....
We present a unified framework for reasoning about worst-case regret bounds for learning algorithms. This framework is based on the theory of duality of convex functions. It brin...
Concentration inequalities that incorporate variance information (such as Bernstein's or Bennett's inequality) are often significantly tighter than counterparts (such as...
This work deals with trajectory optimization for a network of robotic sensors sampling a spatio-temporal random field. We examine the problem of minimizing over the space of networ...