Sciweavers

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

12

IJCAI
2007

favoriteEmaildiscussreport

140views Artificial Intelligence» more IJCAI 2007»

Utile Distinctions for Relational Reinforcement Learning

13 years 6 months ago

Utile Distinctions for Relational Reinforcement Learning

Download www.ijcai.org

We introduce an approach to autonomously creating state space abstractions for an online reinforcement learning agent using a relational representation. Our approach uses a tree-based function approximation derived from McCallum’s [1995] UTree algorithm. We have extended this approach to use a relational representation where relational observations are represented by attributed graphs [McGovern et al., 2003]. We address the challenges introduced by a relational representation by using stochastic sampling to manage the search space [Srinivasan, 1999] and temporal sampling to manage autocorrelation [Jensen and Neville, 2002]. Relational UTree incorporates Iterative Tree Induction [Utgoff et al., 1997] to allow it to adapt to changing environments. We empirically demonstrate that Relational UTree performs better than similar relational learning methods [Finney et al., 2002; Driessens et al., 2001] in a blocks world domain. We also demonstrate that Relational UTree can learn to play a s...

William Dabney, Amy McGovern

Real-time Traffic

Artificial Intelligence | IJCAI 2007 | Relational Observations | Relational Representation | Relational UTree |

claim paper

Related Content

» Crossdomain transfer for reinforcement learning

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

» Building Relational World Models for Reinforcement Learning

» An acquisition of the relation between vision and action using selforganizing map and rein...

» Autonomous shaping knowledge transfer in reinforcement learning

» Reinforcement Learning Task Clustering

» Using background knowledge to speed reinforcement learning in physical agents

» Using Homomorphisms to Transfer Options across Continuous Reinforcement Learning Domains

» SelfOptimizing Memory Controllers A Reinforcement Learning Approach

Post Info
More Details (n/a)

Added	29 Oct 2010
Updated	29 Oct 2010
Type	Conference
Year	2007
Where	IJCAI
Authors	William Dabney, Amy McGovern

Comments (0)