Occupancy information ratio: infinite-horizon, information-directed, parameterized policy search

DOI10.1137/22M1536650MaRDI QIDQ6652398zbMATH OpenFDO

Authors Wesley A. Suttle, Alec Koppel, Ji Liu

Publication date 12 December 2024

Published in SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1137/22M1536650

zbMATH Keywords

nonconvex optimizationpolicy gradient methodsreinforcement learning

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Computational methods for problems pertaining to operations research and mathematical programming (90-08) Stochastic systems in control theory (general) (93E03) Optimal stochastic control (93E20) Stochastic learning and adaptive control (93E35)

Recommendations

• Learning to optimize via information-directed sampling
• scientific article; zbMATH DE number 1753152
• Policy iterations for reinforcement learning problems in continuous time and space -- fundamental theory and methods
• On the theory of policy gradient methods: optimality, approximation, and distribution shift
• Dynamic policy programming

Cites work

• An information-theoretic analysis of Thompson sampling
• Entropy and information theory.
• Fractional Programming. I, Duality
• Generalized Concavity
• Global convergence of policy gradient methods to (almost) locally optimal policies
• Global optimality guarantees for policy gradient methods
• scientific article; zbMATH DE number 3644821 (Why is no real title available?)
• scientific article; zbMATH DE number 5348356 (Why is no real title available?)
• scientific article; zbMATH DE number 1972910 (Why is no real title available?)
• scientific article; zbMATH DE number 2107836 (Why is no real title available?)
• Natural actor-critic algorithms
• Reinforcement Learning, Bit by Bit
• Reinforcement learning. An introduction
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• Stochastic approximation methods for constrained and unconstrained systems

This page was built for publication: Occupancy information ratio: infinite-horizon, information-directed, parameterized policy search

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6652398)