Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

11

ECML
2006
Springer

favoriteEmaildiscussreport

88views Machine Learning» more ECML 2006»

Reinforcement Learning for MDPs with Constraints

13 years 6 months ago

Reinforcement Learning for MDPs with Constraints

Download www.peter-geibel.de

In this article, I will consider Markov Decision Processes with two criteria, each defined as the expected value of an infinite horizon cumulative return. The second criterion is either itself subject to an inequality constraint, or there is maximum allowable probability that the single returns violate the constraint. I describe and discuss three new reinforcement learning approaches for solving such control problems.

Peter Geibel

Real-time Traffic

ECML 2006 | Horizon Cumulative Return | Inequality Constraint | Machine Learning | Maximum Allowable Probability |

claim paper

Related Content

» TeXDYNA Hierarchical Reinforcement Learning in Factored MDPs

» Between MDPs and SemiMDPs A Framework for Temporal Abstraction in Reinforcement Learning

» Online Linear Regression and Its Application to ModelBased Reinforcement Learning

» Discovering Hierarchy in Reinforcement Learning with HEXQ

» Exploiting Additive Structure in Factored MDPs for Reinforcement Learning

» Automatic Feature Selection for ModelBased Reinforcement Learning in Factored MDPs

» Optimism in Reinforcement Learning Based on KullbackLeibler Divergence

» MultipleGoal Reinforcement Learning with Modular Sarsa0

» Hierarchical reinforcement learning with subpolicies specializing for learned subgoals

Post Info
More Details (n/a)

Added	13 Oct 2010
Updated	13 Oct 2010
Type	Conference
Year	2006
Where	ECML
Authors	Peter Geibel

Comments (0)