@article{qgraphboundedqlearningstabilizingmodel1,
  title = {Qgraph-bounded Q-learning: Stabilizing Model-Free Off-Policy Deep Reinforcement Learning},
  author = {Sabrina Hoppe and Marc Toussaint},
  year = {2020},
  eprint = {2007.07582},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2007.07582v1},
}