@article{frombanditsmodeltodeepdeterministic,
  title = {From Bandits Model to Deep Deterministic Policy Gradient, Reinforcement Learning with Contextual Information},
  author = {Zhendong Shi and Xiaoli Wei and Ercan E. Kuruoglu},
  year = {2023},
  eprint = {2310.00642},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2310.00642v1},
}