Dynamic policy programming

MaRDI QIDQ5405224zbMATH OpenFDO

Authors Mohammad Gheshlaghi Azar, Vicenç Gómez, Hilbert J. Kappen

Publication date 1 April 2014

Full work available at URL http://www.jmlr.org/papers/v13/azar12a.html

zbMATH Keywords

approximate dynamic programmingfunction approximationMarkov decision processesMonte-Carlo methodsreinforcement learning

Mathematics Subject Classification ID

Dynamic programming (90C39) Markov and semi-Markov decision processes (90C40)

Recommendations

• Empirical dynamic programming
• Approximate policy iteration: a survey and some new methods
• scientific article; zbMATH DE number 4003938
• Approximate policy iteration for Markov decision processes via quantitative adaptive aggregations
• Continuous state dynamic programming via nonexpansive approximation

Cited in

(12)

• Reduced complexity dynamic programming based on policy iteration
• Rollout sampling approximate policy iteration
• Kernel dynamic policy programming: applicable reinforcement learning to robot systems with high dimensional states
• On linear and super-linear convergence of natural policy gradient algorithm
• Empirical dynamic programming
• Approximate policy iteration: a survey and some new methods
• Applications of variable discounting dynamic programming to iterated function systems and related problems
• Safe policy iteration: a monotonically improving approximate policy iteration approach
• On the theory of policy gradient methods: optimality, approximation, and distribution shift
• Time-varying policy rule under learning
• Value Iteration is Optic Composition
• Occupancy information ratio: infinite-horizon, information-directed, parameterized policy search

This page was built for publication: Dynamic policy programming

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5405224)