@article{learningrlpoliciesforjointbeamforming,
  title = {Learning RL-Policies for Joint Beamforming Without Exploration: A Batch Constrained Off-Policy Approach},
  author = {Heasung Kim and Sravan Kumar Ankireddy},
  year = {2023},
  eprint = {2310.08660},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2310.08660v2},
}