@inproceedings{ijcai2025p552,
  title     = {Maximum Entropy Softmax Policy Gradient via Entropy Advantage Estimation},
  author    = {Choe, Jean Seong Bjorn and Kim, Jong-kook},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {4958--4966},
  year      = {2025},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2025/552},
  url       = {https://doi.org/10.24963/ijcai.2025/552},
}