This paper discusses parameter-based exploration methods for reinforcement learning. Parameter-based methods perturb parameters of a general function approximator directly, rather than adding noise to the resulting actions. Parameter-based exploration unifies reinforcement learning and black-box optimization, and has several advantages over action perturbation. We review two recent parameter-ex...

This paper describes a new task-contracting schema for multi-agent manufacturing control based on soft computing. It aims to apply fuzzy techniques to implement a real-time multi-criteria task-contracting mechanism for part flow control in manufacturing floor. For comparison purposes, the paper also considers other recently proposed evolutionary strategies to adapt and optimize agents’ decision...

With the rapid pace of population ageing, tuberculosis (TB) in the elderly increasingly becomes a public health challenge. Despite the increasing burden and high risks for TB in the elderly, targeted strategy has not been well understood and evaluated. We undertook a scoping review to identify current TB strategies, research and policy gaps in the elderly and summarized the results within a str...

The paper presents an approach to the acquisition of texture models of specific objects under the following assumptions: (I) the system has to recognize objects on a sequence of images. (2) images of a sequence demonstrate the variability of conditions under which objects are perceived (e.g., resolution. lighting, surface positioning), (3) an observer or objects can move, (4) the extraction of ...

Previous research in organisational sociology has focused on how organisational forms are evolved, transformed and sustained. This paper continues in this line of enquiry and tests the role of IT in organisational transformation. The transformation of an organisation can be gauged by observing key organisational attributes that are likely to feature in transformed (new) organisations. Following...

in this paper, an intelligent control strategy based on combination of the “flatness based control technique” and the “perturbation and observation (p&o;) mppt algorithm” is developed and investigated to control a hybrid electric energy source (heps). this ehps is composed of a fuel cell system (fc) and a solar panel (sp), as the main source and a supercapacitor bank (sc), as the auxiliary sour...

We consider the numerical evolutionary optimization of dynamic molecular alignment by shaped femtosecond laser pulses. We study a simplified model of this quantum control problem, which allows the full physical investigation of the optimal solutions. By using specific variants of Derandomized Evolution Strategies, subject to parameterizations which are known to be superior for this problem, the...

One of the most important techniques in human-robot communication is gesture recognition. If robots can read intentions from human gestures, the communication process will be smoother and more natural. Processing for gesture recognition typically consists of two parts: feature extraction and gesture classification. In most works, these are independently designed and evaluated by their own crite...

Cumulative step-size adaptation (CSA) based on path length control is regarded as a robust alternative to the standard mutative self-adaptation technique in evolution strategies (ES), guaranteeing an almost optimal control of the mutation operator. This paper shows that the underlying basic assumption in CSA--the perpendicularity of expected consecutive steps--does not necessarily guarantee opt...

the present study adopts the perspective that metacognitive strategy instruction is bound to occur inside the classroom especially on oral tasks. accordingly, the researchers investigated whether metacognitive strategy instruction prior to oral tasks was more successful than conventional ways in improving efl learners’ oral proficiency. to this end, 56 participants studying in a language school...