Computer Science – Artificial Intelligence
Scientific paper
2008-12-25
Proc. 2nd Conf. on Artificial General Intelligence (AGI 2009) pages 61-66
Computer Science
Artificial Intelligence
7 pages
Scientific paper
General purpose intelligent learning agents cycle through (complex,non-MDP) sequences of observations, actions, and rewards. On the other hand, reinforcement learning is well-developed for small finite state Markov Decision Processes (MDPs). So far it is an art performed by human designers to extract the right state representation out of the bare observations, i.e. to reduce the agent setup to the MDP framework. Before we can think of mechanizing this search for suitable MDPs, we need a formal objective criterion. The main contribution of this article is to develop such a criterion. I also integrate the various parts into one learning algorithm. Extensions to more realistic dynamic Bayesian networks are developed in a companion article.
No associations
LandOfFree
Feature Markov Decision Processes does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Feature Markov Decision Processes, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Feature Markov Decision Processes will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-436754