Hölder continuity of the policy function approximation in the value function approximation

2007 ◽  
Vol 43 (5) ◽  
pp. 629-639 ◽  
Author(s):  
Wilfredo L. Maldonado ◽  
B.F. Svaiter
2013 ◽  
Vol 756-759 ◽  
pp. 3967-3971
Author(s):  
Bo Yan Ren ◽  
Zheng Qin ◽  
Feng Fei Zhao

Linear value function approximation with binary features is important in the research of Reinforcement Learning (RL). When updating the value function, it is necessary to generate a feature vector which contains the features that should be updated. In high dimensional domains, the generation process will take lot more time, which reduces the performance of algorithm a lot. Hence, this paper introduces Optional Feature Vector Generation (OFVG) algorithm as an improved method to generate feature vectors that can be combined with any online, value-based RL method that uses and expands binary features. This paper shows empirically that OFVG performs well in high dimensional domains.


2008 ◽  
Vol 25 (3) ◽  
pp. 287-304 ◽  
Author(s):  
Masashi Sugiyama ◽  
Hirotaka Hachiya ◽  
Christopher Towell ◽  
Sethu Vijayakumar

2014 ◽  
Vol 15 (3) ◽  
pp. 223-231 ◽  
Author(s):  
Feng-fei Zhao ◽  
Zheng Qin ◽  
Zhuo Shao ◽  
Jun Fang ◽  
Bo-yan Ren

Sign in / Sign up

Export Citation Format

Share Document