Joint measurements of qubit observables have recently been studied in conjunction with quantum information processing tasks such as cloning. Considerations of such joint measurements have until now been restricted to a certain class of observables that can be characterized by a form of covariance. Here we investigate conditions for the joint measurability of arbitrary pairs of qubit observables...

Temporal difference (TD) learning methods (Sutton & Barto 1998) have become popular reinforcement learning techniques in recent years. TD methods, relying on function approximators to generalize learning to novel situations, have had some experimental successes and have been shown to exhibit some desirable properties in theory, but have often been found slow in practice. This paper presents met...

We provide non-asymptotic bounds for the well-known temporal difference learning algorithm TD(0) with linear function approximators. These include high-probability bounds as well as bounds in expectation. Our analysis suggests that a step-size inversely proportional to the number of iterations cannot guarantee optimal rate of convergence unless we assume (partial) knowledge of the stationary di...

We present new results about the temporal-difference learning algorithm, as applied to approximating the cost-to-go function of a Markov chain using linear function approximators. The algorithm we analyze performs on-line updating of a parameter vector during a single endless trajectory of an aperiodic irreducible finite state Markov chain. Results include convergence (with probability 1), a ch...

We present a Fourier neural network (FNN) that can be mapped directly to the decomposition. The choice of activation and loss function yields results replicate series expansion closely while preserving straightforward architecture with single hidden layer. simplicity this facilitates integration any other higher-complexity networks, at data pre- or postprocessing stage. validate FNN on naturall...

This paper is an overview of cascade-correlation neural networks which form a specific class inside neural network function approximators. They are based on a special architecture which autonomously adapts to the application and makes the training much more efficient than the widely used backpropagation algorithm. This survey describes the cascade-correlation architecture variants, shows import...

With this paper we describe a well suited, scalable problem for reinforcement learning approaches in the field of mobile robots. We show a suitable representation of the problem for a reinforcement approach and present our results with a model based standard algorithm. Two different approximators for the value function are used, a grid based approximator and a neural network based approximator.

we prove in this paper that the class of reversible synchronous Boltzmann machines is universal for the representation of arbitrary functions defined on finite sets. This completes a similar result from Sussmann in the sequential case. Keywords-Synchronous random fields, Cellular automata, Gibbs distributions, Boltzmann machines. Neural networks.