Convergence of a Q-Learning Variant for Continuous States and Actions
Document Type
Article
Publication Date
2014
Publication Title
Journal of Artificial Intelligence Research
DOI
10.1613/jair.4271
ISSN
1076-9757
Abstract
This paper presents a reinforcement learning algorithm for solving infinite horizon Markov Decision Processes under the expected total discounted reward criterion when both the state and action spaces are continuous. This algorithm is based on Watkins' Q-learning, but uses Nadaraya-Watson kernel smoothing to generalize knowledge to unvisited states. As expected, continuity conditions must be imposed on the mean rewards and transition probabilities. Using results from kernel regression theory, this algorithm is proven capable of producing a Q-value function estimate that is uniformly within an arbitrary tolerance of the true Q-value function with probability one. The algorithm is then applied to an example problem to empirically show convergence as well.
Recommended Citation
Carden, Stephen W..
2014.
"Convergence of a Q-Learning Variant for Continuous States and Actions."
Journal of Artificial Intelligence Research, 49: 705-731.
doi: 10.1613/jair.4271
https://digitalcommons.georgiasouthern.edu/math-sci-facpubs/290
Comments
JAIR is an open access journal and articles are published for free distribution on the internet by the AI Access Foundation.