Reliable off-policy evaluation for reinforcement learning

DOI10.1287/OPRE.2022.2382MaRDI QIDQ6579655FDOQ6579655

Authors: Jie Wang, Rui Gao, Hongyuan Zha 

Publication date: 25 July 2024

Published in: Operations Research (Search for Journal in Brave)

Recommendations

• Proximal reinforcement learning: efficient off-policy evaluation in partially observed Markov decision processes
• Double reinforcement learning for efficient off-policy evaluation in Markov decision processes
• Projected state-action balancing weights for offline reinforcement learning
• Efficiently Breaking the Curse of Horizon in Off-Policy Evaluation with Double Reinforcement Learning
• Off-policy evaluation in partially observed Markov decision processes under sequential ignorability

zbMATH Keywords

uncertainty quantificationreinforcement learningWasserstein robust optimization

Mathematics Subject Classification ID

Decision theory (91B06)

Cited In (4)

• Pessimistic value iteration for multi-task data sharing in offline reinforcement learning
• Proximal reinforcement learning: efficient off-policy evaluation in partially observed Markov decision processes
• Projected state-action balancing weights for offline reinforcement learning
• Off-policy evaluation for tabular reinforcement learning with synthetic trajectories

This page was built for publication: Reliable off-policy evaluation for reinforcement learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6579655)