Article contents
Gradient estimation for smooth stopping criteria
Published online by Cambridge University Press: 15 June 2022
Abstract
We establish sufficient conditions for differentiability of the expected cost collected over a discrete-time Markov chain until it enters a given set. The parameter with respect to which differentiability is analysed may simultaneously affect the Markov chain and the set defining the stopping criterion. The general statements on differentiability lead to unbiased gradient estimators.
- Type
- Original Article
- Information
- Copyright
- © The Author(s), 2022. Published by Cambridge University Press on behalf of Applied Probability Trust
References
- 1
- Cited by