@inproceedings{ijcai2023p522,
  title     = {Towards Long-delayed Sparsity: Learning a Better Transformer through Reward Redistribution},
  author    = {Zhu, Tianchen and Qiu, Yue and Zhou, Haoyi and Li, Jianxin},
  booktitle = {Proceedings of the Thirty-Second International Joint Conference on
               Artificial Intelligence, {IJCAI-23}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Edith Elkind},
  pages     = {4693--4701},
  year      = {2023},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2023/522},
  url       = {https://doi.org/10.24963/ijcai.2023/522},
}