Towards a Pretrained Model for Restless Bandits via Multi-arm Generalization. (arXiv:2310.14526v3 [cs.LG] UPDATED)

Restless multi-arm bandits (RMABs), a class of resource allocation problems
with broad application in areas such as healthcare, online advertising, and
anti-poaching, have recently been studied from a multi-agent reinforcement
learning perspective. Prior RMAB research suffers from several limitations,
e.g., it fails to adequately address continuous states, and requires retraining
from scratch when arms opt-in and opt-out over time, a common challenge in many
real world applications. We address these limitations by developing a neural
network-based pre-trained model (PreFeRMAB) that …

advertising agent application arm arxiv class continuous cs.lg healthcare limitations multi-agent online advertising perspective prior reinforcement reinforcement learning research via