Nearly Minimax Optimal Offline Reinforcement Learning with Linear Function Approximation: Single-Agent MDP and Markov Game

Nearly Minimax Optimal Offline Reinforcement Learning with Linear Function Approximation: Single-Agent MDP and Markov Game. Xiong, W., Han, Z., Shi, C., Shen, C., Wang, L., & Zhang, T. arXiv (Cornell University), 2022.

Paper bibtex

@article{2572,
  author = {Wei Xiong and Zhongchao Han and Chengshuai Shi and Cong Shen and Liwei Wang and Tong Zhang},
  title = {Nearly Minimax Optimal Offline Reinforcement Learning with Linear
  Function Approximation: Single-Agent MDP and Markov Game},
  year = {2022},
  journal = {arXiv (Cornell University)},
  url = {https://arxiv.org/abs/2205.15512}
}

Downloads: 0