In this paper, a novel approach termed Dynamic Self-Generated Fuzzy Q-Learning (DSGFQL) for automatically generating Fuzzy Neural Networks (FNNs) is presented. The structure and premises of FNNs are to be generated through the reward evaluation and unsupervised approaches while the consequents are trained via a Fuzzy Q-Learning (FQL) approach. The proposed DSGFQL methodology can automatically c...

in this paper, we consider first-order fuzzy differential equations with initial value conditions. the convergence, consistency and stability of difference method for approximating the solution of fuzzy differential equations involving generalized h-differentiability, are studied. then the local truncation error is defined and sufficient conditions for convergence, consistency and stability of ...

In this paper, we introduce the notion of Q-fuzzification of M-subgroups in a near-ring and investigate some related properties. Characterization of Anti Q-fuzzy Msubgroups with respect to s-norm is given.

In this paper we introduce the notion of fuzzy bitopological ideals .The concept of fuzzy pairwise local function is also introduced here by utilizing the q-neighborhood structure for a fuzzy topological space .These concepts are discussed fuzzy bitopologies and several relations between different fuzzy bitopological ideals .

Recently, Reich and Zaslavski have studied a new inexact iterative scheme for fixed points of contractive and nonexpansive multifunctions. In 2011, Aleomraninejad, et. al. generalized some of their results to Suzuki-type multifunctions.  The study of iterative schemes for various classes of contractive and nonexpansive mappings is a central topic in fixed point theory. The importance of Banach ...

The sequence space m(φ,∆m, p) of fuzzy real numbers for 0 < p < 1 and 1 ≤ p < ∞, are introduced. Some properties of the sequence space like solidness, symmetricity, convergence-free etc. are studied.

We address two open theoretical questions in Policy Gradient Reinforcement Learning. The first concerns the efficacy of using function approximation to represent the state action value function, Q. Theory is presented showing that linear function approximation representations of Q can degrade the rate of convergence of performance gradient estimates by a factor of O(ML) relative to when no func...

in this paper, we establish the theory of fuzzy ideal convergence on completely distributive lattices and give characterizations of some topological notions. we also study fuzzy limit structures and discuss the relationship between fuzzy co-topologies and fuzzy limit structures.

This paper presents a novel adaptive neuro-fuzzy inference system based on interval Gaussian type-2 fuzzy sets in the antecedent part and Gaussian type-1 fuzzy sets as coefficients of linear combination of input variables in the consequent part. The capability of the proposed ANFIS2 for function approximation and dynamical system identification is remarkable. The structure of ANFIS2 is very sim...