A type of flexible models in the form of a neural network (NN) with evolving structure is treated in the paper. We refer to models with amorphous structure as flexible models. There is a close link between different types of flexible models: fuzzy models, fuzzy NN, and general regression model. All of them are proven universal approximators and some of them (Takagi-Sugeno fuzzy model with singl...

We introduce optimal energy shaping as an enhancement of classical passivity-based control methods. A promising feature passivity theory, alongside stability, has traditionally claimed to be intuitive performance tuning along the execution a given task. However, systematic approach for adjusting within passive framework yet developed, each method relies on few and problem-specific practical ins...

– When using the Lyapunov synthesis approach to construct a stable fuzzy control system, one important way is to regard the fuzzy systems as approximators to approximate the unknown functions in the system to be controlled. Concerning the unknownness of the unknown functions, generally there are two cases: a completely unknown case, and a partly unknown case. However, most of the schemes presen...

This paper presents a new approach for modelling nonlinear dynamic processes (NDP). It is based on autoregressive with exogenous (NARX) inputs model structure and deep convolutional fuzzy system (DCFS). The DCFS hierarchical structure, which can overcome the deficiency of general systems when facing high dimensional data. For relieving curse dimensionality, as well improving approximation perfo...

Several reinforcement-learning techniques have already been applied to the Acrobot control problem, using linear function approximators to estimate the value function. In this paper, we present experimental results obtained by using a feedforward neural network instead. The learning algorithm used was model-based continuous TD(λ). It generated an efficient controller, producing a high-accuracy ...

The classical approaches in fuzzy control (Zadeh and Mamdani) deal with dense rule bases. When this is not the case, i.e. in sparse rule bases, one has to choose another method. Fuzzy rule interpolation (proposed first by Kóczy and Hirota [15]) offers a possibility to construct fuzzy controllers (KH controllers) under such conditions. The main result of this paper shows that the KH interpolatio...

In a great diversity of knowledge areas, the variables that are involved in the behavior of a complex system, perform normally, a non-linear system. The search of a function that express those behavior, requires techniques as mathematics optimization techniques or others. The new paradigms introduced in the soft computing, as fuzzy logic, neuronal networks, genetics algorithms and the fusion of...

A generalized probability mixture density governs an additive fuzzy system. The fuzzy system’s if-then rules correspond to the mixed probability densities. An additive fuzzy system computes an output by adding its fired rules and then averaging the result. The mixture’s convex structure yields Bayes theorems that give the probability of which rules fired or which combined fuzzy systems fired fo...

We present policy gradient results within the framework of linearly-solvable MDPs. For the first time, compatible function approximators and natural policy gradients are obtained by estimating the cost-to-go function, rather than the (much larger) state-action advantage function as is necessary in traditional MDPs. We also develop the first compatible function approximators and natural policy g...