@article{modelbasedreinforcementlearningfrom,
  title = {Model-based Reinforcement Learning from Signal Temporal Logic Specifications},
  author = {Parv Kapoor and Anand Balakrishnan and Jyotirmoy V. Deshmukh},
  year = {2020},
  eprint = {2011.04950},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2011.04950v1},
}