Off-policy evaluation for tabular reinforcement learning with synthetic trajectories

DOI10.1007/s11222-023-10351-yzbMath1529.62039OpenAlexW4388767681MaRDI QIDQ6190662

Yu-Qiang Li, Wei-wei Wang, Xianyi Wu

Publication date: 6 February 2024

Published in: Statistics and Computing (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s11222-023-10351-y

zbMATH Keywords

importance samplingMarkov decision processreinforcement learningoff-policy evaluationsynthetic trajectories

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08)

Cites Work

• Unnamed Item
• Bias and Variance Approximation in Value Function Estimates
• Marginal Mean Models for Dynamic Regimes
• Optimal Dynamic Treatment Regimes
• Estimating Dynamic Treatment Regimes in Mobile Health Using V-Learning