Simulation of partially observed Markov decision process and dynamic quality improvement

1997 ◽  
Vol 32 (4) ◽  
pp. 691-700 ◽  
Author(s):  
Nancy Gautreau ◽  
Soumaya Yacout ◽  
Réjean Hall
Keyword(s):  
Quality Improvement ◽  
Markov Decision Process ◽  
Decision Process ◽  
Partially Observed ◽  
Markov Decision ◽  
Dynamic Quality

Exploitation-Oriented Learning PS-r#

2009 ◽  
Vol 13 (6) ◽  
pp. 624-630 ◽  
Author(s):  
Kazuteru Miyazaki ◽  
◽  
Shigenobu Kobayashi ◽  
Keyword(s):  
Random Walk ◽  
Reinforcement Learning ◽  
Markov Decision Process ◽  
Decision Process ◽  
Sensory Input ◽  
Numerical Examples ◽  
Novel Approach ◽  
Partially Observed ◽  
Markov Decision ◽  
Directed Learning

Exploitation-oriented learning (XoL) is a novel approach to goal-directed learning from interaction. Reinforcement learning is much more focused on learning and ensures optimality in Markov decision process (MDP) environments, XoL involves learning a rational policy that obtains rewards continuously and very quickly. PS-r*, a form of XoL, involves learning a useful rational policy not inferior to the random walk in the partially observed Markov decision process (POMDP) where reward types number one. PS-r*, however, requires O(MN2) memory where N is the number of sensory input types and M is an action. We propose PS-r#for learning a useful rational policy in the POMDP using O(MN) memory. PS-r#effectiveness is confirmed in numerical examples.

Sign in / Sign up

Export Citation Format

Share Document