Off-policy confidence interval estimation with confounded markov decision process

C Shi, J Zhu, Y Shen, S Luo, H Zhu… - Journal of the American …, 2024 - Taylor & Francis
This article is concerned with constructing a confidence interval for a target policy's value
offline based on a pre-collected observational data in infinite horizon settings. Most of the …
被引用次数：34 相关文章

Off-Policy Confidence Interval Estimation with Confounded Markov Decision Process

C Shi, J Zhu, S Ye, S Luo, H Zhu… - Journal of the American …, 2024 - ingentaconnect.com
This article is concerned with constructing a confidence interval for a target policy's value
offline based on a pre-collected observational data in infinite horizon settings. Most of the …

Off-Policy Confidence Interval Estimation with Confounded Markov Decision Process

C Shi, J Zhu, Y Shen, S Luo, H Zhu, R Song - arXiv preprint arXiv …, 2022 - arxiv.org
This paper is concerned with constructing a confidence interval for a target policy's value
offline based on a pre-collected observational data in infinite horizon settings. Most of the …

Off-policy confidence interval estimation with confounded Markov decision process

C Shi, J Zhu, Y Shen, S Luo, H Zhu… - Journal of the American …, 2022 - eprints.lse.ac.uk
This paper is concerned with constructing a confidence interval for a target policy's value
offline based on a pre-collected observational data in infinite horizon settings. Most of the …

Off-Policy Confidence Interval Estimation with Confounded Markov Decision Process

C Shi, J Zhu, S Ye, S Luo, H Zhu… - Journal of the American …, 2024 - ideas.repec.org
This article is concerned with constructing a confidence interval for a target policy's value
offline based on a pre-collected observational data in infinite horizon settings. Most of the …
[PDF] researchgate.net

[PDF][PDF] Off-Policy Confidence Interval Estimation with Confounded Markov Decision Process

C Shi, J Zhu, Y Shen, S Luo, H Zhu, R Song - researchgate.net
This paper is concerned with constructing a confidence interval for a target policy's value
offline based on a pre-collected observational data in infinite horizon settings. Most of the …

Off-Policy Confidence Interval Estimation with Confounded Markov Decision Process

C Shi, J Zhu, S Ye, S Luo, H Zhu… - Journal of the American …, 2024 - econpapers.repec.org
This article is concerned with constructing a confidence interval for a target policy's value
offline based on a pre-collected observational data in infinite horizon settings. Most of the …

Off-Policy Confidence Interval Estimation with Confounded Markov Decision Process

C Shi, J Zhu, Y Shen, S Luo, H Zhu, R Song - arXiv e-prints, 2022 - ui.adsabs.harvard.edu
This paper is concerned with constructing a confidence interval for a target policy's value
offline based on a pre-collected observational data in infinite horizon settings. Most of the …

Off-policy confidence interval estimation with confounded Markov decision process

C Shi, J Zhu, Y Shen, S Luo, H Zhu, R Song - 2022 - econpapers.repec.org
This article is concerned with constructing a confidence interval for a target policy's value
offline based on a pre-collected observational data in infinite horizon settings. Most of the …

Off-policy confidence interval estimation with confounded Markov decision process

C Shi, J Zhu, Y Shen, S Luo, H Zhu, R Song - 2022 - ideas.repec.org
This article is concerned with constructing a confidence interval for a target policy's value
offline based on a pre-collected observational data in infinite horizon settings. Most of the …