@misc{wen2024entropyregularizedtokenlevelpolicyoptimization,
      title={Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement}, 
      author={Muning Wen and Junwei Liao and Cheng Deng and Jun Wang and Weinan Zhang and Ying Wen},
      year={2024},
      eprint={2402.06700},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2402.06700}, 
}