@article{areinforcementlearningmethodfor,
  title = {A Reinforcement Learning Method for Environments with Stochastic Variables: Post-Decision Proximal Policy Optimization with Dual Critic Networks},
  author = {Leonardo Kanashiro Felizardo and Edoardo Fadda and Paolo Brandimarte and Emilio Del-Moral-Hernandez and Mariá Cristina Vasconcelos Nascimento},
  year = {2025},
  eprint = {2504.05150},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.05150v1},
}