1 Hit in 1.5 sec

NeurWIN: Neural Whittle Index Network For Restless Bandits Via Deep RL [article]

Khaled Nakhleh, Santosh Ganji, Ping-Chun Hsieh, I-Hong Hou, Srinivas Shakkottai
2022 arXiv   pre-print
This paper proposes NeurWIN, a neural Whittle index network that seeks to learn the Whittle indices for any restless bandits by leveraging mathematical properties of the Whittle indices.  ...  We show that a neural network that produces the Whittle index is also one that produces the optimal control for a set of Markov decision problems.  ...  NeurWIN Algorithm: Neural Whittle Index Network In this section, we present NeurWIN, a deep-RL algorithm that trains neural networks to predict the Whittle indices.  ... 
arXiv:2110.02128v2 fatcat:l4im36uuabhljdougq33a3ptju