Provably Efficient Reinforcement Learning for Adversarial Restless Multi-Armed Bandits with Unknown Transitions and Bandit Feedback

arXiv:2405.00950v1 Announce Type: new
Abstract: Restless multi-armed bandits (RMAB) play a central role in modeling sequential decision making problems under an instantaneous activation constraint that at most B arms can be activated at any decision epoch. Each restless arm is endowed with a state that evolves independently according to a Markov decision process regardless of being activated or not. In this paper, we consider the task of learning in episodic RMAB with unknown transition functions and adversarial rewards, which can …

abstract adversarial arm arxiv cs.ai cs.lg decision decision making feedback making modeling multi-armed bandits reinforcement reinforcement learning role state stat.ml transitions type