I-Hong Hou — accepted AI-conference papers

2022

DeepTOP: Deep Threshold-Optimal Policy for MDPs and RMABs

NeurIPS 2022accept

We consider the problem of learning the optimal threshold policy for control problems. Threshold policies make control decisions by evaluating whether an element of the system state exceeds a certain threshold, whose value is determined by other elements of the system state. By leveraging the monoto…

Cited by 10 Source ↗PDF ↗code ↗Scholar ↗

2021

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

Khaled Nakhleh, Santosh Ganji, Ping-Chun Hsieh, I-Hong Hou, Srinivas Shakkottai

NeurIPS 2021poster

Whittle index policy is a powerful tool to obtain asymptotically optimal solutions for the notoriously intractable problem of restless bandits. However, finding the Whittle indices remains a difficult problem for many practical restless bandits with convoluted transition kernels. This paper proposes…

Cited by 51 Source ↗PDF ↗code ↗Scholar ↗