My research focuses on how to design learning environments that a) immerse participants in the authentic practices and ways of thinking of engineering, arts, and sciences; b) dynamically respond to learners' individual and collective skill development; c) actively support learning facilitation by teachers, parents, and other caregivers; and d) certify learning accomplishments through valid measures of competence derived from analyses of learners' participation in these environments. The Educational Research group of the Wisconsin Institutes for Discovery, in which I am a postdoc, is pursuing these aims through the creation of educational video games. Though we have world-leading expertise in the design of engaging and authentic games about science, we are just beginning to explore how to imbue these environments with the responsive dynamism that goals b, c, d (above) require. Assessment of learning over time is at the heart of the challenges we now face in realizing them. In this talk, I'll present some of the core theories of learning that guide our work, discuss essential challenges to their application in practice, and give an overview of our work on Trails Forward, a game we are creating in collaboration with Michael Ferris. Then, I will explain how the essence of the assessment and responsive design challenge we now face is essentially one of modeling time series of interactions between learners and game, as well as between learners and one-another, as evidence for learning, illustrating how the learning (and modeling) goals we have are fundamentally different than those that the educational data mining literature has tackled thus far. I will conclude with an invitation for collaboration between the UW/WID Education Research and Optimization communities.<?xml:namespace prefix = o />