Hierarchical state decompositions address the curse-ofdimensionality in Q-learning methods for reinforcement learning (RL) but can suffer from suboptimality. In addressing this, w...
Erik G. Schultink, Ruggiero Cavallo, David C. Park...
Technology can play an important role in enabling people to interact with each other. The Web is one such technology with the affordances for sharing information and for connectin...
Procedural representations of control policies have two advantages when facing the scale-up problem in learning tasks. First they are implicit, with potential for inductive genera...
We present a novel method for learning with Gaussian process regression in a hierarchical Bayesian framework. In a first step, kernel matrices on a fixed set of input points are l...
While much work on learning in planning focused on learning domain physics (i.e., action models), and search control knowledge, little attention has been paid towards learning use...
Nan Li, William Cushing, Subbarao Kambhampati, Sun...