Taskflow-oriented programming merges concepts from structured programming, hardware description, and mark-up languages. A mark-up language such as XML supports a well-defined schema that can capture the decomposition of a program into a hierarchy of tasks. A hardware description language such as VHDL relies on well-defined and explicit input/output port definitions to create, at any level of hi...

{ Taskkow-oriented programming merges concepts from structured programming, hardware description, and markup languages. A markup language such as XML supports a well-deened schema that can capture the decomposition of a program into a hierarchy of tasks. A hardware description language such as VHDL relies on well-deened and explicit input/output port deenitions to create, at any level of hierar...

We introduce the collaborative multi-output Gaussian process (GP) model for learning dependent tasks with very large datasets. The model fosters task correlations by mixing sparse processes and sharing multiple sets of inducing points. This facilitates the application of variational inference and the derivation of an evidence lower bound that decomposes across inputs and outputs. We learn all t...

The effect of error feedback on the accuracy of output task types such as editing task, text reconstruction task, picture cued writing task, and dictogloss task, has not been clearly explored. Following arguments concerning that the combination of both corrective feedback and output makes it difficult to determine whether their effects were in combination or alone, the purpose of the present st...

Framed in a cognitive approach to task-supported L2 vocabulary learning, the present study used a pedagogical approach to investigate the relative effectiveness of tasks with different involvement loads on the vocabulary knowledge of Iranian EFL learners. The goal was to investigate the way that the construct of involvement load is related to the Input Hypothesis (Krashen, 1985) and the Output ...

In order to be successfully executed, collaborative tasks performed by two agents often require a cooperative strategy learned. this work, we propose constraint-based multi-agent reinforcement learning approach called constrained soft actor critic (C-MSAC) train control policies for simulated performing multi-phase tasks. Given task with n $$ phases, the first − 1 n-1 phases are treated as cons...