Student models for Intelligent Computer Assisted Language Learning (ICALL) have largely focused on the acquisition of grammatical structures. In this paper, we motivate a broader p...
Real-valued random hidden variables can be useful for modelling latent structure that explains correlations among observed variables. I propose a simple unit that adds zero-mean G...
Motivated by the interest in relational reinforcement learning, we introduce a novel relational Bellman update operator called ReBel. It employs a constraint logic programming lan...
Kristian Kersting, Martijn Van Otterlo, Luc De Rae...
We describe a method for learning formulas in firstorder logic using a brute-force, smallest-first search. The method is exceedingly simple. It generates all irreducible well-form...
Abstract. We present a domain-independent algorithm for planning that computes macros in a novel way. Our algorithm computes macros “on-the-fly” for a given set of states and ...