Skip to content

Opening book details…

Can I read Learning Representation and Control in Markov Decision Processes: New Frontiers on EtoBox?

Learning Representation and Control in Markov Decision Processes: New Frontiers by Mahadevan S. is a nonfiction available to read on EtoBox.

What is Learning Representation and Control in Markov Decision Processes: New Frontiers about?

Из серии Foundations and Trends in Machine Learning издательства NOWPress, 2008, -163 pp. This paper describes a novel machine learning framework for solving sequential decision problems called Markov decision processes (MDPs) by iteratively computing low-dimensional representations and approximately optimal policies. A unified mathematical framework for learning representation and optimal control in MDPs is presented based on a class of singular operators called Laplacians, whose matrix representations have nonpositive off-diagonal elements and zero row sums. Exact solutions of discounted and average-reward MDPs are expressed in terms of a generalized spectral inverse of the Laplacian called the Drazin inverse. A generic algorithm called representation policy iteration (RPI) is presented which interleaves computing low-dimensional representations and approximately optimal policies. Two approaches for dimensionality reduction of MDPs are described based on geometric and reward-sensitive regularization, whereby low-dimensional representations are formed by diagonalization or dilation of Laplacian operators. Model-based and model-free variants of the RPI algorithm are presented; the

Who reads Learning Representation and Control in Markov Decision Processes: New Frontiers?

It is typically read by self-directed learners exploring a subject in depth.

Common subject areas: history, science, philosophy, social sciences.

Author
Mahadevan S.
Language
EN
Category
nonfiction
Subjects
Computer Science, Cybernetics, Stem

More by Mahadevan S.

Browse all works by Mahadevan S.

Similar books