Nature计算科学综述：经由准实验，从观察数据中推测因果关系(22)

65. Zhang, J. & Bareinboim, E. Markov Decision Processes with Unobserved Confounders: A Causal Approach. Technical Report (R-23) (Columbia CausalAI Laboratory, 2016).
66. Mnih, V. et al. Human-level control through deep reinforcement learning. Nature 518, 529–533 (2015).
67. Lansdell, B., Triantafllou, S. & Kording, K. Rarely-switching linear bandits: optimization of causal efects for the real world. Preprint at https://arxiv.org/ abs/1905.13121 (2019).
68. Adadi, A. & Berrada, M. Peeking inside the black-box: a survey on explainable artifcial intelligence (XAI). IEEE Access 6, 52138–52160 (2018).
69. Zhao, Q. & Hastie, T. Causal interpretations of black-box models. J. Bus. Econ. Stat. 39, 272–281 (2021).
70. Morafah, R., Karami, M., Guo, R., Raglin, A. & Liu, H. Causal interpretability for machine learning—problems, methods and evaluation. ACM SIGKDD Explor. Newsl. 22, 18–33 (2020).
71. Ribeiro, M. T., Singh, S. & Guestrin, C. ‘Why should I trust you?’: Explaining the predictions of any classifer. In Proc. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 1135–1144 (Association for Computing Machinery, 2016); https://doi.org/10.1145/2939672.2939778