@article{rewardmodellearningvsdirectpolicy,
  title = {Reward Model Learning vs. Direct Policy Optimization: A Comparative Analysis of Learning from Human Preferences},
  author = {Andi Nika and Debmalya Mandal and Parameswaran Kamalaruban and Georgios Tzannetos and Goran Radanović and Adish Singla},
  year = {2024},
  eprint = {2403.01857},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2403.01857v2},
}