Sciweavers

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

12

FLAIRS
2006

favoriteEmaildiscussreport

103views Artificial Intelligence» more FLAIRS 2006»

Using Active Relocation to Aid Reinforcement Learning

13 years 5 months ago

Using Active Relocation to Aid Reinforcement Learning

Download www.cs.utexas.edu

We propose a new framework for aiding a reinforcement learner by allowing it to relocate, or move, to a state it selects so as to decrease the number of steps it needs to take in order to develop an effective policy. The framework requires a minimal amount of human involvement or expertise and assumes a cost for each relocation. Several methods for taking advantage of the ability to relocate are proposed, and their effectiveness is tested in two commonly-used domains.

Lilyana Mihalkova, Raymond J. Mooney

Real-time Traffic

Artificial Intelligence | Effective Policy | FLAIRS 2006 | Human Involvement | Reinforcement Learner |

claim paper

Related Content

» Could Active Perception Aid Navigation of Partially Observable Grid Worlds

» Reinforcement learning with limited reinforcement using Bayes risk for active learning in ...

» Using Reinforcement Learning to Improve Exploration Trajectories for Error Minimization

» Active Learning for Reward Estimation in Inverse Reinforcement Learning

» Efficient exploration through active learning for value function approximation in reinforc...

» Selecting actions for resourcebounded information extraction using reinforcement learning

» Robot reinforcement learning using EEGbased reward signals

» Using relative novelty to identify useful temporal abstractions in reinforcement learning

» Active object recognition by view integration and reinforcement learning

Post Info
More Details (n/a)

Added	31 Oct 2010
Updated	31 Oct 2010
Type	Conference
Year	2006
Where	FLAIRS
Authors	Lilyana Mihalkova, Raymond J. Mooney

Comments (0)