Deep architectures are families of functions corresponding to deep circuits. Deep Learning algorithms are based on parametrizing such circuits and tuning their parameters so as to ...
Abstract. Auction-based electronic commerce is an increasingly interesting domain for AI researchers. In this paper we present an attempt towards the construction of trading agents...
Metamodels are functions with calibrated parameters, used actions and simplifications of the simulation model. A metamodel exposes the system’s input-output relationship and ca...
We present the first temporal-difference learning algorithm for off-policy control with unrestricted linear function approximation whose per-time-step complexity is linear in the ...
An agent who bases his actions upon explicit logical formulae has at any given point in time a finite set of formulae he has computed. Closure or consistency conditions on this se...