@article{isreinforcementlearningnotfornatural,
  title = {Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization},
  author = {Rajkumar Ramamurthy and Prithviraj Ammanabrolu and Kianté Brantley and Jack Hessel and Rafet Sifa and Christian Bauckhage and Hannaneh Hajishirzi and Yejin Choi},
  year = {2022},
  eprint = {2210.01241},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2210.01241v3},
}