We introduce skill chaining, a skill discovery method for reinforcement learning agents in continuous domains. Skill chaining produces chains of skills leading to an end-of-task reward. We demonstrate experimentally that skill chaining is able to create appropriate skills in a challenging continuous domain and that doing so results in performance gains.

The impetus for conducting the present study came from Thornbury's (2005) approach to teach speaking in which he claimed that awareness-raising techniques, along with appropriation strategies, facilitate the process of teaching and learning speaking. Therefore, the present study attempted to explore the impact of the appropriation-based syllabus to teach speaking by using chunks-on-card...

The aim of this study is to make a new attempt to explore the potential of integrating game strategies with automatic speech recognition technologies to provide learners with individual opportunities for English pronunciation learning. The study developed the Game Embedded CALL (GeCALL) system with two activities for on-line speaking practice. For the drill practice, learners get immediate scor...

We ask whether the role of employer learning in the wage-setting process depends on skill type and skill importance to productivity. Combining data from the NLSY79 with O*NET data, we use Armed Services Vocational Aptitude Battery scores to measure seven distinct types of pre-market skills that employers cannot readily observe, and O*NET importance scores to measure the importance of each skill...

BACKGROUND Learning styles determine how people manage new information. Evidence-based medicine (EBM) involves the management of information in clinical practice. As a consequence, the way in which a person uses EBM can be related to his or her learning style. In order to tailor EBM education to the individual learner, this study aims to determine whether there is a relationship between an indi...

This paper aims to enhance the performance of a TTS system by generating various speaking styles. First we describe three speaking styles (Radio News, Political Address and Conversation) and compare the prosodic features found in these authentic styles with the prosody in “neutral” speech uttered by the eLite TTS system ([1]). Differences concern about 20 prosodic characteristics (F0 span, spee...

Discriminating speaking styles is an important issue in speech recognition, speaker recognition and speaker segmentation. This paper compares distance measures between Gaussian distributions for discriminating speaking styles. The Mahalanobis distance, the Bhattacharyya distance and the Kullback-Leibler divergence, which are in common use for a definition as a distance measure between Gaussian ...

We examined the controlling factors that allow a prompted skill to become autonomous in a discrete-trials implementation of Touchette's (1971) progressively delayed prompting procedure, but our subjects were rats rather than children with disabilities. Our prompted skill was a left-right lever-press sequence guided by two panel lights. We manipulated (a) the effectiveness of the guiding lights ...

Transfer (i.e., the application of a learned skill in a novel context) is an important and desirable outcome of motor skill learning. While much research has been devoted to understanding transfer of explicit skills the mechanisms of skill transfer after incidental learning remain poorly understood. The aim of this study was to (1) examine the effect of practice schedule on transfer and (2) inv...

Research has shown that retrieval of learned information is better when the original learning context is reinstated during testing than when this context is changed. Recently, such contextual dependencies have also been found for perceptual-motor behavior. The current study investigated the nature of context-dependent learning in the discrete sequence production task, and in addition examined w...