Effcient inference in Markov control problems.
Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence, UAI 2011
221 - 229.
Markov control algorithms that perform smooth, non-greedy updates of the policy have been shown to be very general and versatile, with policy gradient and Expectation Maximisation algorithms being particularly popular. For these algorithms, marginal inference of the reward weighted trajectory distribution is required to perform policy updates. We discuss a new exact inference algorithm for these marginals in the finite horizon case that is more effcient than the standard approach based on classical forwardbackward recursions. We also provide a principled extension to infinite horizon Markov Decision Problems that explicitly accounts for an infinite horizon. This extension provides a novel algorithm for both policy gradients and Expectation Maximisation in infinite horizon problems.
|Title:||Effcient inference in Markov control problems|
|UCL classification:||UCL > School of BEAMS > Faculty of Engineering Science > Computer Science|
Archive Staff Only