Assessment of work performed by paired students: a pedagogical experience

“Teamwork” is one of the abilities most valued by employers. In [16] we describe the process of adapting to the ECTS methodologies (for ongoing assessment), a course in computer programming for students in a technical degree (Marine Engineering, UPM) not specifically dedicated to computing. As a further step in this process we have emphasized cooperative learning. For this, the students were paired and the work of each pair was evaluated via surprise tests taken and graded jointly, and constituting a substantial part of the final grade. Here we document this experience, discussing methodological aspects, describing indicators for measuring the impact of these methodologies on the educational experience, and reporting on the students’ opinion of it.

Linear Bayes policy for learning in contextual-bandits

Machine and Statistical Learning techniques are used in almost all online advertisement systems. The problem of discovering which content is more demanded (e.g. receive more clicks) can be modeled as a multi-armed bandit problem. Contextual bandits (i.e., bandits with covariates, side information or associative reinforcement learning) associate, to each specific content, several features that define the “context” in which it appears (e.g. user, web page, time, region). This problem can be studied in the stochastic/statistical setting by means of the conditional probability paradigm using the Bayes’ theorem. However, for very large contextual information and/or real-time constraints, the exact calculation of the Bayes’ rule is computationally infeasible. In this article, we present a method that is able to handle large contextual information for learning in contextual-bandits problems. This method was tested in the Challenge on Yahoo! dataset at ICML2012’s Workshop “new Challenges for Exploration & Exploitation 3”, obtaining the second place. Its basic exploration policy is deterministic in the sense that for the same input data (as a time-series) the same results are obtained. We address the deterministic exploration vs. exploitation issue, explaining the way in which the proposed method deterministically finds an effective dynamic trade-off based solely in the input-data, in contrast to other methods that use a random number generator.