Active Learning of Parameterized Skills
Bruno da Silva, George Konidaris, Andrew G. Barto · 2014
We introduce a method for actively learning pa-rameterized skills. Parameterized skills are flex-ible behaviors that can solve any task drawn from a distribution of parameterized reinforce-ment learning problems. Approaches to learning such skills have been proposed, but limited atten-tion has been given to identifying which train-ing tasks allow for rapid skill acquisition. We construct a non-parametric Bayesian model of skill performance and derive analytical expres-sions for a novel acquisition criterion capable of identifying tasks that maximize expected im-provement in skill performance. We also intro-duce a spatiotemporal kernel tailored for non-stationary skill performance models. The pro-posed method is agnostic to policy and skill rep-resentation and scales independently of task di-mensionality. We evaluate it on a non-linear sim-ulated catapult control problem over arbitrarily mountainous terrains. 1.