Unbounded dynamic programming via the Q-transform
Year of publication: |
2022
|
---|---|
Authors: | Ma, Qingyin ; Stachurski, John ; Akira Toda, Alexis |
Published in: |
Journal of mathematical economics. - Amsterdam [u.a.] : Elsevier, ISSN 0304-4068, ZDB-ID 217625-7. - Vol. 100.2022, p. 1-13
|
Subject: | Reinforcement learning | Dynamic programming | Optimality | Dynamische Optimierung | Theorie | Theory | Mathematische Optimierung | Mathematical programming | Lernprozess | Learning process |
-
On boundedness of Q-learning iterates for stochastic shortest path problems
Yu, Huizhen, (2013)
-
Has dynamic programming improved decision making?
Rust, John, (2019)
-
Efficient reinforcement learning in deterministic systems with value function generalization
Wen, Zheng, (2017)
- More ...
-
The income fluctuation problem and the evolution of wealth
Ma, Qingyin, (2020)
-
A theory of the saving rate of the rich
Ma, Qingyin, (2021)
-
Asymptotic linearity of consumption functions and computational efficiency
Ma, Qingyin, (2022)
- More ...