NeurWIN: Neural Whittle Index Network For Restless Bandits Via Deep RL
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 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. This property motivates using deep reinforcement learning for the training of NeurWIN. We demonstrate the utility of NeurWIN by evaluating its performance for three recently studied restless bandit problems. Our experiment results show that the performance of NeurWIN is significantly better than other RL algorithms.
Code (1)
Tasks
Deep Reinforcement LearningSimilar Papers 제목 키워드 기반
ContextWIN: Whittle Index Based Mixture-of-Experts Neural Model For Restless Bandits Via Deep RL
This study introduces ContextWIN, a novel architecture that extends the Neural Whittle Index Network (NeurWIN) model to address Restless Multi-Armed Bandit (RMAB) problems with a context-aware approach. By integrating a …
Decision MakingMixture-of-ExpertsRecommendation SystemsConditions for indexability of restless bandits and an O(K^3) algorithm to compute Whittle index
Restless bandits are a class of sequential resource allocation problems concerned with allocating one or more resources among several alternative processes where the evolution of the process depends on the resource alloc…
Whittle index based Q-learning for restless bandits with average reward
A novel reinforcement learning algorithm is introduced for multiarmed restless bandits with average reward, using the paradigms of Q-learning and Whittle index. Specifically, we leverage the structure of the Whittle inde…
Q-Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Optimistic Whittle Index Policy: Online Learning for Restless Bandits
Restless multi-armed bandits (RMABs) extend multi-armed bandits to allow for stateful arms, where the state of each arm evolves restlessly with different transitions depending on whether that arm is pulled. Solving RMABs…
Multi-Armed BanditsTwo families of indexable partially observable restless bandits and Whittle index computation
We consider the restless bandits with general state space under partial observability with two observational models: first, the state of each bandit is not observable at all, and second, the state of each bandit is obser…