the application of deep learning and planning techniques, with the aim of constructing generalized plans capable of solving multiple problem instances. We construct a Deep Neural Network that, given an abstract problem state, predicts both (i) the best action to be taken from that state and (ii) the generalized “role” of the object being manipulated. The neural network was tested on two classical planning domains: the blocks world domain and the logistic domain. Results indicate that neural networks are capable of making such
predictions with high accuracy, indicating a promising new framework for approaching generalized planning problems.
This study aims to produce efficient and effective group writing workshops for students within the Barrett Honors College at Arizona State University. To balance two opposing theories in writing center pedagogy - the direct instruction theory and the student-led/ collaborative theory - this study also aims to determine whether a balanced combination of these approaches in writing workshops will increase student confidence in their writing abilities. Several writing workshops were held over Zoom utilizing a combination of direct teaching methods and collaborative techniques. Students were then surveyed to determine whether they found the workshops helpful, learned new skills, and/or grew more confident in their abilities. The student responses proved the hypothesis that a combined approach leads to an increase in student confidence.