@article{acceleratingproximalpolicyoptimization,
  title = {Accelerating Proximal Policy Optimization Learning Using Task Prediction for Solving Environments with Delayed Rewards},
  author = {Ahmad Ahmad and Mehdi Kermanshah and Kevin Leahy and Zachary Serlin and Ho Chit Siu and Makai Mann and Cristian-Ioan Vasile and Roberto Tron and Calin Belta},
  year = {2024},
  eprint = {2411.17861},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2411.17861v3},
}