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.

Current concerns over reforming engineering education have focused attention on helping students develop skills and an adaptive expertise. Phenomenological guidelines for instruction along these lines can be understood as arising out of an emerging theory of thinking and learning built on results in the neural, cognitive, and behavioral sciences. We outline this framework and consider some of i...

This study extends the conventional and superficial notion of measuring digital skills by proposing definitions for operational, formal, information and strategic skills. The main purpose was to identify individual skill related problems that users experience when navigating the Internet. In particular, lower levels of education and aging seem to contribute to the amount of experienced operatio...