@article{explorationdrivenpolicyoptimizationin, title = {Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization}, author = {Yihan Du and Anna Winnicki and Gal Dalal and Shie Mannor and R. Srikant}, year = {2024}, eprint = {2402.10342}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2402.10342v2}, }