PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Autonomous Exploration For Navigating In MDPs
Shiau Hong Lim and Peter Auer
In: COLT 2012, 25-27 Jun 2012, Edinburgh, Scotland.


While intrinsically motivated learning agents hold considerable promise to overcome limitations of more supervised learning systems, quantitative evaluation and theoretical analysis of such agents are difficult. We propose to consider a restricted setting for autonomous learning where systematic evaluation of learning performance is possible. In this setting the agent needs to learn to navigate in a Markov Decision Process where extrinsic rewards are not present or are ignored. We present a learning algorithm for this scenario and evaluate it by the amount of exploration it uses to learn the environment.

EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Theory & Algorithms
ID Code:8473
Deposited By:Shiau Hong Lim
Deposited On:02 February 2012