Faceted Browser

32 document(s) found.

Limit to site collection (autonweb) Limit to site variant (branch main, language en)
Order by:
Open this query in the query search page

Filters:

Tags equals Markov Decision Processes

Remove all

1-10 of 32 Next >

Algorithms for Approximating Optimal Value Functions in Acyclic Domains

Document Type: Paper
Tags: Markov Decision Processes, Optimization, Reinforcement Learning

Some of the most successful recent applications of reinforcement learning have used neural networks and the TD() algorithm to learn evaluation functions. In this paper, we examine the intuition that TD() operates by approximating asynchronous value iteration. We note that on the important subcla...

Andrew Moore

Document Type: Person
Tags: Link Analysis, Auton Fast Classifiers, Statistical Data Mining for Astrophysics, Cached Sufficient Statistics, Efficient Statistical Algorithms, Spatial Statistics, Life Science Data Mining, Logistic Regression, Locally Weighted Learning, GDA, AD-trees, Bayesian Networks, Kernel Density Estimation, Kd-trees and Ball-trees, Mixture Models, WSARE, Reinforcement Learning, Active Learning, Markov Decision Processes, K Nearest Neighbor, Astrostatistics, Clustering, Memory-based Learning, Biosurveillance, Applications, Optimization, Association Rules

Andrew began his career writing video-games for an obscure British personal computer. He rapidly became a thousandaire and retired to academia, where he received a PhD from the University of Cambridge in 1991. He researched robot learning as a Post-doc working with Chris Atkeson, and then moved ...

Applying online search techniques to Continuous-State reinforcement learning

Document Type: Paper
Tags: Markov Decision Processes

In this paper, we describe methods for efficiently computing better solutions to control problems in continuous state spaces. We provide algorithms that exploit online search to boost the power of very approximate value functions discovered by traditional reinforcement learning techniques. We ex...

Autonomous Helicopter Control using Reinforcement Learning Policy Search Methods

Document Type: Paper
Tags: Markov Decision Processes, Applications, Reinforcement Learning

Abstract Many control problems in the robotics field can be cast as Partially Observed Markovian Decision Problems (POMDPs), an optimal control formalism. Finding optimal solutions to such problems in general, however is known to be intractable. It has often been observed that in practice, simpl...

Covariant Policy Search

Document Type: Paper
Tags: Markov Decision Processes, Optimization, Reinforcement Learning

Abstract We investigate the problem of non-covariant behavior of policy gradient reinforcement learning algorithms. The policy gradient approach is amenable to analysis by information geometric methods. This leads us to propose a natural metric on controller parameterization that results from co...

Distributed Value Functions

Document Type: Paper
Tags: Markov Decision Processes, Optimization, Reinforcement Learning

Many interesting problems, such as power grids, network switches, and traffic flow, that are candidates for solving with reinforcement learning (RL), also have properties that make distributed solutions desirable. We propose an algorithm for distributed reinforcement learning based on distributi...

Drew Bagnell

Document Type: Person
Tags: Markov Decision Processes, Reinforcement Learning

I grew up in Palm Bay, Florida. I attended the University of Florida and studied electrical engineering while working for Keith Doty in robotics. After graduating and spending a short time as a hardware and software designer in the telecom industry, I joined the robotics institute to study machi...

Generalization in Reinforcement Learning: Safely Approximating the Value Function

Document Type: Paper
Tags: Markov Decision Processes, Reinforcement Learning

A straightforward approach to the curse of dimensionality in reinforcement learning and dynamic programming is to replace the lookup table with a generalizing function approximator such as a neural net. Although this has been successful in the domain of backgammon, there is no guarantee of conve...

Influence and Variance of a Markov Chain: Application to adaptive discretization in optimal control

Document Type: Paper
Tags: Markov Decision Processes, Kd-trees and Ball-trees, Reinforcement Learning

This paper addresses the difficult problem of deciding where to refine the resolution of adaptive discretizations for solving continuous time-and-space deterministic optimal control problems. We introduce two measures, influence and variance of a Markov chain. Influence measures the extent to wh...

Jeff Schneider

Document Type: Person
Tags: Markov Decision Processes, Link Analysis, Statistical Data Mining for Astrophysics, Astrostatistics, Cached Sufficient Statistics, Memory-based Learning, Efficient Statistical Algorithms, Spatial Statistics, Locally Weighted Learning, GDA, Biosurveillance, Bayesian Networks, Kd-trees and Ball-trees, Applications, Optimization, WSARE, Active Learning

Dr. Jeff Schneider is an associate research professor in the Carnegie Mellon University School of Computer Science. He received his PhD in Computer Science from the University of Rochester in 1995. He has over 15 years experience developing, publishing, and applying machine learning algorithms...