Visualization of the learning processes is a powerful way to help students to understand their curricula and the structure behind them. CME2 is a prototype software of this favour...
We model reinforcement learning as the problem of learning to control a Partially Observable Markov Decision Process ( ¢¡¤£¦¥§ ), and focus on gradient ascent approache...
Exact learning of half-spaces over finite subsets of IRn from membership queries is considered. We describe the minimum set of labelled examples separating the target concept from ...
Realistic domains for learning possess regularities that make it possible to generalize experience across related states. This paper explores an environment-modeling framework tha...
A number of natural models for learning in the limit is introduced to deal with the situation when a learner is required to provide a grammar covering the input even if only a par...