Research on reinforcement learning has demonstrated promising results in manifold applications and domains. Still, efficiently learning effective robot behaviors is very difficult, due to unstructured scenarios, high uncertainties, and large state dimensionality (e.g. multi-agent systems or hyper-redundant robots). To alleviate this problem, we present DOP, a deep model-based reinforcement lear...

The feasibility of positive energy yield in systems with the p–11B reaction is considered here by considering refined (optimistic) data on rate. analysis was carried out within traditional framework for magnetic confinement systems, but without taking into account a particular type plasma configuration. balance both ions and electrons. particles includes all species as well products fusion (alp...

Robot path planning algorithms for finding a goal in a unknown environment focus on completeness rather than optimality. In this paper, we investigate several strategies for using map information, however incomplete or approximate, to reduce the cost of the robot’s traverse. The strategies are based on optimistic, pessimistic, and average value assumptions about the unknown portions of the robo...

This paper studies abstraction and refinement techniques in the setting of multi-valued model checking for the μ-calculus. Two dimensions of abstractions are identified and studied: Abstraction by joining states of the underlying multi-valued Kripke structure as well as abstraction of truth values, for each following both an optimistic and pessimistic account. It is shown that our notion of abs...

   Recently, Farzipoor Saen [Journal of the Operational Research Society, 60(11), 1575–1582 (2009)] proposed a method based on data envelopment analysis to identify optimistic efficient suppliers in the presence of nondiscretionary factors-imprecise data. This short communication aims at showing a computational error in computing the value of preference intensity parameter in Farzipoor Saen’s [...

This paper suggests  a novel approach for ranking the most applicable fuzzy numbers, i.e.  $LR$-fuzzy numbers. Applying the  $alpha$-optimistic values of a fuzzy number, a preference criterion is proposed for ranking fuzzy numbers using the Credibility index. The main properties of the proposed  preference criterion  are also studied.  Moreover, the proposed method is   applied for ranking fuzz...

Explanatory style (ES) reflects the way people usually explain disparate bad or good events involving the self. The purpose of this study was twofold: (a) to test whether ES moderates the effect of perceived ability on students' expectancies and subjective task value, and (b) to explore the mediating effects of success expectancies and subjective task value in the relationships between ES and s...

Many sequential decision-making problems require an agent to reason about both multiple objectives and uncertainty regarding the environment’s state. Such problems can be naturally modelled as multi-objective partially observable Markov decision processes (MOPOMDPs). We propose optimistic linear support with alpha reuse (OLSAR), which computes a bounded approximation of the optimal solution set...