Dynamic programming paper for VaR Markov decision processes in continuous space released
Get up to speed
Xian Chen, Erick Delage, and Weikai Wang published an academic paper that for the first time proves the validity of dynamic programming equations for value-at-risk Markov decision processes (VaR MDPs) in continuous space, covering both finite-horizon and infinite-horizon scenarios. Previously, relevant dynamic programming equations were only derived and verified under finite state and action spaces, with continuous space scenarios remaining unsolved for a long time. This framework can be used to characterize optimal dynamic strategies for optimal execution problems with VaR objectives, solving an open problem in this field.
AI-generated from reports · 3 hr agoUpdated
Coverage timeline
Follow the coverage to understand different sides of the event.
- arXiv q-finA Dynamic Programming Approach for Value-at-Risk Markov Decision Processes in Continuous Spaces
This study is the first to prove the validity of dynamic programming equations for Value-at-Risk Markov Decision Processes (VaR MDPs) in continuous spaces, covering both finite-horizon and infinite-horizon scenarios. Previously, related dynamic programming equations had only been derived and verified in finite state and action spaces, leaving the continuous-space problem unresolved for a long time. This framework can be used to characterize optimal dynamic strategies for optimal execution problems with VaR objectives, solving an open problem in the field.
Trend of this event
Not enough consecutive observations yet; trend is not drawn.