@article{learningwithoutcriticsrevisitinggrpoincl,
  title = {Learning Without Critics? Revisiting GRPO in Classical Reinforcement Learning Environments},
  author = {Bryan L. M. de Oliveira and Felipe V. Frujeri and Marcos P. C. M. Queiroz and Luana G. B. Martins and Telma W. de L. Soares and Luckeciano C. Melo},
  year = {2025},
  eprint = {2511.03527},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2511.03527},
}