Realistic domains for learning possess regularities that make it possible to generalize experience across related states. This paper explores an environment-modeling framework tha...
We present an approach to semi-supervised learning based on an exponential family characterization. Our approach generalizes previous work on coupled priors for hybrid generative/...
While in general trading off exploration and exploitation in reinforcement learning is hard, under some formulations relatively simple solutions exist. Optimal decision thresholds ...
We present new results on the well-studied problem of learning DNF expressions. We prove that an algorithm due to Kushilevitz and Mansour [13] can be used to weakly learn DNF form...
Avrim Blum, Merrick L. Furst, Jeffrey C. Jackson, ...
This paper reports findings from a survey on students' attitude towards the use of Web 2.0 tools in a Romanian university. The purpose of the study is threefold: i) establish ...