.png){kind=icon}
.png){kind=icon}
Return
Using Convex Switching Techniques for Partially Observable Decision Processes
.png){kind=icon}
PRE
AI
DOI：10.1109/TAC.2015.2505403.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We present and examine a novel method for obtaining solutions to specific discrete-time optimal control problems. Our approach is based on linear state dynamics and convexity assumptions commonly satisfied in practical applications. We show that the important class of optimal switching problems under partial observation is covered by our methodology, and we exploit specific model features to achieve simple algorithmic form of a numerical solution.
Keywords:
Approximate dynamic programming
Markov Decision
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7
Papers:
1.3W
Citations:
6.7W