Regret Analysis of Policy Gradient Algorithm for Infinite Horizon Average Reward Markov Decision Processes

Bai et al. "Regret Analysis of Policy Gradient Algorithm for Infinite Horizon Average Reward Markov Decision Processes." AAAI Conference on Artificial Intelligence, 2024. doi:10.1609/AAAI.V38I10.28973

[Bai et al. "Regret Analysis of Policy Gradient Algorithm for Infinite Horizon Average Reward Markov Decision Processes." AAAI Conference on Artificial Intelligence, 2024.](https://mlanthology.org/aaai/2024/bai2024aaai-regret/) doi:10.1609/AAAI.V38I10.28973

@inproceedings{bai2024aaai-regret,
  title     = {{Regret Analysis of Policy Gradient Algorithm for Infinite Horizon Average Reward Markov Decision Processes}},
  author    = {Bai, Qinbo and Mondal, Washim Uddin and Aggarwal, Vaneet},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2024},
  pages     = {10980-10988},
  doi       = {10.1609/AAAI.V38I10.28973},
  url       = {https://mlanthology.org/aaai/2024/bai2024aaai-regret/}
}