Beyond Expected Return: Accounting for Policy Reproducibility When Evaluating Reinforcement Learning Algorithms

Flageat et al. "Beyond Expected Return: Accounting for Policy Reproducibility When Evaluating Reinforcement Learning Algorithms." AAAI Conference on Artificial Intelligence, 2024. doi:10.1609/AAAI.V38I11.29090

[Flageat et al. "Beyond Expected Return: Accounting for Policy Reproducibility When Evaluating Reinforcement Learning Algorithms." AAAI Conference on Artificial Intelligence, 2024.](https://mlanthology.org/aaai/2024/flageat2024aaai-beyond/) doi:10.1609/AAAI.V38I11.29090

@inproceedings{flageat2024aaai-beyond,
  title     = {{Beyond Expected Return: Accounting for Policy Reproducibility When Evaluating Reinforcement Learning Algorithms}},
  author    = {Flageat, Manon and Lim, Bryan and Cully, Antoine},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2024},
  pages     = {12024-12032},
  doi       = {10.1609/AAAI.V38I11.29090},
  url       = {https://mlanthology.org/aaai/2024/flageat2024aaai-beyond/}
}