.png){kind=icon}
返回
Robust Q-learning algorithm for Markov decision processes under Wasserstein uncertainty
.png){kind=icon}
PRE
AI
DOI：10.1016/j.automatica.2024.111825.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We present a novel Q-learning algorithm tailored to solve distributionally robust Markov decision problems where the corresponding ambiguity set of transition probabilities for the underlying Markov decision process is a Wasserstein ball around a (possibly estimated) reference measure. We prove convergence of the presented algorithm and provide several examples also using real data to illustrate both the tractability of our algorithm as well as the benefits of considering distributional robustness when solving stochastic optimal control problems, in particular when the estimated distributions turn out to be misspecified in practice. (c) 2024 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.
Keyword:
Markov decision process
Wasserstein uncertainty
Distributionally robust optimization
Reinforcement learning
Q-learning
期刊
IF:
5.9
论文数:
1.2W
被引数:
5.2W
机构
引用论文
分享收藏The use of titanium dioxide particles embedded in anionic hydrogel composite for photocatalytic degradation of methylene blue.png)
SPE Polymers
SPE PolymersIF0
PREAI
分享收藏Facile Synthesis, Characterization, Nanocrystal Growth and Photoluminescence Properties of GeS NanowiresNano
NanoIF0
PREAI
分享收藏Study of bi-directional buck-boost converter topologies for application in electrical vehicle motor drives应用于电动汽车电机驱动的双向buck-boost变换器拓扑研究
PREAI
分享收藏Mechanical, but not infective, pacemaker erosion may be successfully managed by re-implantation of pacemakers.Heart
OAAI
HeartIF0
OAAI分享收藏
查看更多内容