The learning classifier system XCS is an iterative rulelearning system that evolves rule structures based on gradient-based prediction and rule quality estimates. Besides classifi...
Martin V. Butz, Pier Luca Lanzi, Stewart W. Wilson
The results of the latest International Probabilistic Planning Competition (IPPC-2008) indicate that the presence of dead ends, states with no trajectory to the goal, makes MDPs h...
We propose a novel variant of the conjugate gradient algorithm, Kernel Conjugate Gradient (KCG), designed to speed up learning for kernel machines with differentiable loss functio...
In this work, a generalized method for learning from sequence of unlabelled data points based on unsupervised order-preserving regression is proposed. Sequence learning is a funda...
straction is a useful tool for agents interacting with environments. Good state abstractions are compact, reuseable, and easy to learn from sample data. This paper and extends two...