Several algorithms for learning near-optimal policies in Markov Decision Processes have been analyzed and proven efficient. Empirical results have suggested that Model-based Inter...
It is common in classification methods to first place data in a vector space and then learn decision boundaries. We propose reversing that process: for fixed decision boundaries, ...
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...
Relativized options combine model minimization methods and a hierarchical reinforcement learning framework to derive compact reduced representations of a related family of tasks. ...
This paper reports developments on a best description template for teaching methods, whose descriptive elements will eventually be mapped to the elements of the IMS Learning Desig...