Approximate Value Iteration with Temporally Extended Actions

DOI10.1613/JAIR.4676MaRDI QIDQ2941739zbMATH OpenOpenAlexFDO

Authors Timothy A. Mann, Shie Mannor, Doina Precup

Publication date 25 August 2015

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

Full work available at URL https://doi.org/10.1613/jair.4676

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Incremental Value Iteration for Time-Aggregated Markov-Decision Processes
• scientific article; zbMATH DE number 1509479
• On the existence of fixed points for approximate value iteration and temporal-difference learning
• Approximate Value Iteration for Risk-Aware Markov Decision Processes
• Iteratively extending time horizon reinforcement learning.
• Value iteration for long-run average reward in Markov decision processes
• Value and Policy Function Approximations in Infinite-Horizon Optimization Problems
• Complexity bounds for approximately solving discounted MDPs by value iterations

Cited in

(3)

• scientific article; zbMATH DE number 2086978 (Why is no real title available?)
• Reward machines: exploiting reward function structure in reinforcement learning
• Planning in hierarchical reinforcement learning: guarantees for using local policies

This page was built for publication: Approximate Value Iteration with Temporally Extended Actions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2941739)