Exploiting action impact regularity and exogenous state variables for offline reinforcement learning

DOI10.1613/JAIR.1.14580MaRDI QIDQ6488780zbMATH OpenFDO

Authors Vincent S. Liu, James R. Wright, Martha White

Publication date 23 October 2023

Published in The Journal of Artificial Intelligence Research (JAIR) (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1613/JAIR.1.14580

zbMATH Keywords

batch reinforcement learningoffline reinforcement learningreal-world reinforcement learningreinforcement learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Offline reinforcement learning with representations for actions
• Settling the sample complexity of model-based offline reinforcement learning
• Pessimistic value iteration for multi-task data sharing in offline reinforcement learning
• Projected state-action balancing weights for offline reinforcement learning
• Offline reinforcement learning with task hierarchies

Cites work

• 10.1162/153244303765208377
• A Knapsack Secretary Problem with Applications
• Bandit algorithms
• scientific article; zbMATH DE number 5957269 (Why is no real title available?)
• Learning Near-Optimal Policies with Bellman-Residual Minimization Based Fitted Policy Iteration and a Single Sample Path
• Near-optimal reinforcement learning in polynomial time
• Performance Bounds in $L_p$‐norm for Approximate Value Iteration
• The Secretary Problem and Its Extensions: A Review
• Using Stochastic Approximation Methods to Compute Optimal Base-Stock Levels in Inventory Control Problems

Cited in

(2)

• Offline reinforcement learning with representations for actions
• Pessimistic value iteration for multi-task data sharing in offline reinforcement learning

This page was built for publication: Exploiting action impact regularity and exogenous state variables for offline reinforcement learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6488780)