Dynamic Choice of State Abstraction in Q-Learning

Frontiers in Artificial Intelligence and Applications, pp. 46-54, 2016.

Cited by: 0|Bibtex|Views10|DOI:https://doi.org/10.3233/978-1-61499-672-9-46
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com

Abstract:

Q-learning associates states and actions of a Markov Decision Process to expected future reward through online learning. In practice, however, when the state space is large and experience is still limited, the algorithm will not find a match between current state and experience unless some details describing states are ignored. On the oth...More

Code:

Data:

Your rating :
0

 

Tags
Comments