@article{qsimmitigatingoverestimationinmultiagent,
  title = {QSIM: Mitigating Overestimation in Multi-Agent Reinforcement Learning via Action Similarity Weighted Q-Learning},
  author = {Yuanjun Li and Bin Zhang and Hao Chen and Zhouyang Jiang and Dapeng Li and Zhiwei Xu},
  year = {2026},
  eprint = {2602.22786},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.22786},
}