The factored policy-gradient planner

DOI10.1016/J.ARTINT.2008.11.008MaRDI QIDQ835832zbMATH OpenOpenAlexWikidataFDO

Authors Olivier Buffet, Douglas Aberdeen

Publication date 31 August 2009

Published in Artificial Intelligence (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.artint.2008.11.008

zbMATH Keywords

reinforcement learningAI planningconcurrent probabilistic temporal planningpolicy-gradient

Mathematics Subject Classification ID

Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20)

Recommendations

• Policy iteration based on stochastic factorization
• Expected policy gradients for reinforcement learning
• Recurrent policy gradients
• Stochastic dynamic programming with factored representations
• Reinforcement learning with factored states and actions
• Policy gradient in continuous time

Cites work

• scientific article; zbMATH DE number 5547912 (Why is no real title available?)
• scientific article; zbMATH DE number 48727 (Why is no real title available?)
• scientific article; zbMATH DE number 1321699 (Why is no real title available?)
• scientific article; zbMATH DE number 2038893 (Why is no real title available?)
• scientific article; zbMATH DE number 1753152 (Why is no real title available?)
• scientific article; zbMATH DE number 1753153 (Why is no real title available?)
• scientific article; zbMATH DE number 1928800 (Why is no real title available?)
• Approximate policy iteration with a policy language bias: solving relational Markov decision processes
• Fast planning through planning graph analysis
• LAO*: A heuristic search algorithm that finds solutions with loops
• Natural actor-critic algorithms
• Practical solution techniques for first-order MDPs
• Relational reinforcement learning
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• The Complexity of Decentralized Control of Markov Decision Processes
• The FF planning system: Fast plan generation through heuristic search
• The factored policy-gradient planner
• Variance reduction techniques for gradient estimates in reinforcement learning

Cited in

(7)

• Probabilistic planning with clear preferences on missing information
• The factored policy-gradient planner
• Discovering hidden structure in factored MDPs
• Practical solution techniques for first-order MDPs
• Planning in artificial intelligence
• Real-time dynamic programming for Markov decision processes with imprecise probabilities
• scientific article; zbMATH DE number 2243416 (Why is no real title available?)

Describes a project that uses

Uses Software

• Graphplan
• PDDL

This page was built for publication: The factored policy-gradient planner

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q835832)