.png){kind=icon}
.png){kind=icon}
Return
Sequential Decision Making With Coherent Risk
.png){kind=icon}
PRE
AI
DOI：10.1109/TAC.2016.2644871.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We provide sampling-based algorithms for optimization under a coherent-risk objective. The class of coherent-risk measures is widely accepted in finance and operations research, among other fields, and encompasses popular risk-measures such as conditional value at risk and mean-semi-deviation. Our approach is suitable for problems in which tuneable parameters control the distribution of the cost, such as in reinforcement learning or approximate dynamic programming with a parameterized policy. Such problems cannot be solved using previous approaches. We consider both static risk measures and time-consistent dynamic risk measures. For static risk measures, our approach is in the spirit of policy gradient methods, while for the dynamic risk measures, we use actor-critic type algorithms.
Keywords:
Coherent risk
dynamic programming
Markov decision processes
policy gradient
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
Organization
View more organizations