Sciweavers

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

8

AUSAI
2008
Springer

favoriteEmaildiscussreport

105views Artificial Intelligence» more AUSAI 2008»

Partial Order Hierarchical Reinforcement Learning

13 years 6 months ago

Partial Order Hierarchical Reinforcement Learning

Download www.cse.unsw.edu.au

In this paper the notion of a partial-order plan is extended to task-hierarchies. We introduce the concept of a partial-order taskhierarchy that decomposes a problem using multi-tasking actions. We go further and show how a problem can be automatically decomposed into a partial-order task-hierarchy, and solved using hierarchical reinforcement learning. The problem structure determines the reduction in memory requirements and learning time.

Bernhard Hengst

Real-time Traffic

Artificial Intelligence | AUSAI 2008 | Multi-tasking Actions | Partial-order Plan | Problem Structure |

claim paper

Related Content

» Reinforcement learning for DECMDPs with changing action sets and partially ordered depende...

» Machine Learning in Hybrid Hierarchical and PartialOrder Planners for Manufacturing Domain...

» Learning Hierarchical Relationships among Partially Ordered Objects with Heterogeneous Att...

» Hierarchical ExplanationBased Reinforcement Learning

» Reinforcement Learning with Hierarchies of Machines

» MarketBased Reinforcement Learning in Partially Observable Worlds

» Generating Hierarchical Structure in Reinforcement Learning from State Variables

» Finding Structure in Reinforcement Learning

» Quadruped Robot Obstacle Negotiation via Reinforcement Learning

Post Info
More Details (n/a)

Added	12 Oct 2010
Updated	12 Oct 2010
Type	Conference
Year	2008
Where	AUSAI
Authors	Bernhard Hengst

Comments (0)