Search for: All records

Proposes a DRL-based pedagogical policy to choose when to present or skip training problems in a logic tutor. Four conditions are compared: control, adaptive DRL, random skipping, and DRL with worked-example choice. DRL policy reduces training time while maintaining posttest performance. 

The assistance dilemma is a well-recognized challenge to determine when and how to provide help during problem solving in intelligent tutoring systems. This dilemma is particularly challenging to address in domains such as logic proofs, where problems can be solved in a variety of ways. In this study, we investigate two data-driven techniques to address the when and how of the assistance dilemma, combining a model that predicts \textit{when} students need help learning efficient strategies, and hints that suggest \textit{what} subgoal to achieve. We conduct a study assessing the impact of the new pedagogical policy against a control policy without these adaptive components. We found empirical evidence which suggests that showing subgoals in training problems upon predictions of the model helped the students who needed it most and improved test performance when compared to their control peers. Our key findings include significantly fewer steps in posttest problem solutions for students with low prior proficiency and significantly reduced help avoidance for all students in training. 

Across human societies, women's economic production and their contributions to childcare are critical in supporting reproductive fitness for themselves, their spouses and children. Yet, the necessity of performing both work and childcare tasks presents women with an adaptive problem in which they must determine how best to allocate their time and energy between these tasks. Women often use cooperative relationships with alloparents to solve this problem, but whether or not women cooperate across different domains (e.g. work and childcare) to access alloparents remains relatively under-explored. Using social network data collected with Shodagor households in Bangladesh, we show that women who need childcare help in order to work draw on cooperative work partners as potential alloparents, and that all women rely heavily on kin, but not reciprocal cooperation for childcare help. These results indicate that Shodagor women strategize to create work and childcare relationships in ways that help solve the adaptive problem they face. We discuss the implications of our results and the example provided by Shodagor women for a broader understanding of women's cooperative relationships, including the importance of socio-ecological circumstances and gendered divisions of labour in shaping women's cooperative strategies.This article is part of the theme issue ‘Cooperation among women: evolutionary and cross-cultural perspectives’.