The Fortuin-Kasteleyn (FK) random cluster model, which can be exactly mapped from the $q$-state Potts spin is a correlated bond percolation model. By extensive Monte Carlo simulations, we study FK representation of critical Ising model ($q=2$) on finite complete graph, i.e. mean-field We provide strong numerical evidence that configuration space for $q=2$ contains an asymptotically vanishing se...

In this research, the relationship between P-wave velocity (Vp) and Electrical Resistivity (ER) parameters with rock mass quality indices is investigated; parameters such as rock mass quality classification (Q) and modified system for sedimentary rocks, known as Qsrm. For making predictive models, about 1200 data-sets extracted from sections drilled in Seymareh and Karun 2 Dam Sites (SDS and KD...

In sequential decision making, it is often important and useful for end users to understand the underlying patterns or causes that lead to the corresponding decisions. However, typical deep reinforcement learning algorithms seldom provide such information due to their black-box nature. In this paper, we present a probabilistic model, Q-LDA, to uncover latent patterns in text-based sequential de...

We present a biologically motivated computational model that is able to anticipate and evaluate multiple hypothetical sensorimotor sequences. Our Model for Anticipation based on Cortical Representations (MACOR) allows a completely parallel search at the neocortical level using assemblies of rate coded neurons for grouping, separation, and selection of sensorimotor sequences. For a vision-contro...

We previously proposed evolutionary fuzzy systems of playing Ms.PacMan for the competitions. As a consequence of the evolution, reflective action rules such that PacMan tries to eat pills effectively until ghosts come close to PacMan are acquired. Such rules works well. However, sometimes it is too reflective so that PacMan go toward ghosts by herself in longer corridors. In this paper, a criti...

K-flats is a model-based linear manifold clustering algorithm which has been successfully applied in many real-world scenarios. Though some previous works have shown that K-flats doesn’t always provide good performance, little effort has been devoted to analyze its inherent deficiency. In this paper, we address this challenge by showing that the deteriorative performance of K-flats can be attri...

We explore deep reinforcement learning methods for multi-agent domains. We begin by analyzing the difficulty of traditional algorithms in the multi-agent case: Q-learning is challenged by an inherent non-stationarity of the environment, while policy gradient suffers from a variance that increases as the number of agents grows. We then present an adaptation of actor-critic methods that considers...