In this paper we develop a theoretical analysis of the performance of sampling-based fitted value iteration (FVI) to solve infinite state-space, discounted-reward Markovian decision problems (MDPs) under the assumption that a generative model of the environment is available. Our main results come in the form of finite-time bounds on the performance of two versions of sampling-based FVI. The con...

compound action potential (cap) of spinal cord represents valuable properties of neural fibers including excitability, rate of myelination and membrane integrity. these properties are measured using amplitude, latency and area under curve of caps recorded from spinal cord. here, the isolated spinal cord was set in a double sucrose gap (dsg) chamber and its response to intracellular stimulation ...

Stepwise regression is a commonly used tool if the order of the linear model to be tted is not known exactly. In this note strategies are proposed for an optimal choice of both the design and the decision rule which selects the adequate model.