Nacionalni portal odprte znanosti

Parametric policy search algorithms are one of the methods of choice for the optimisation of Markov Decision Processes, with Expectation Maximisation and natural gradient ascent being considered the current state of the art in the field. In this article we provide a unifying perspective of these two ...

The viewpoint of solving Markov Decision Processes and their partially observable extension refers to nding policies that max- imise the expected reward. We follow the rephrasing of this problem as learning in a related probabilistic model. Our trans-dimensional distri- bution formulation obtain ...

Solving finite-horizon Markov Decision Processes with stationary policies is a computationally difficult problem. Our dynamic dual decomposition approach uses Lagrange duality to decouple this hard problem into a sequence of tractable sub-problems. The resulting procedure is a straightforward modifi ...