Pretty darn good control: when are approximate solutions better than approximate models

DOI10.1007/S11538-023-01198-5MaRDI QIDQ6077321zbMATH OpenFDO

Authors Felipe Montealegre-Mora, Marcus Lapeyrolerie, Melissa Chapman, Abigail G. Keller, Carl Boettiger

Publication date 25 September 2023

Published in Bulletin of Mathematical Biology (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2308.13654

zbMATH Keywords

uncertaintydecision theoryoptimal controlreinforcement learning

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Environmental economics (natural resource models, harvesting, pollution, etc.) (91B76) Population dynamics (general) (92D25)

Recommendations

• Deep neural networks algorithms for stochastic control problems on finite horizon: convergence analysis
• Approximate policy optimization and adaptive control in regression models
• Model-based reinforcement learning for approximate optimal regulation
• Controlled interacting particle algorithms for simulation-based reinforcement learning
• A projected primal-dual gradient optimal control method for deep reinforcement learning

Cites work

• scientific article; zbMATH DE number 47134 (Why is no real title available?)
• An introduction to deep reinforcement learning
• Model-based Reinforcement Learning: A Survey
• Optimal control theory. Applications to management science and economics

Cited in

(2)

• Deep reinforcement learning for optimal well control in subsurface systems with uncertain geology
• SOLVING DYNAMIC WILDLIFE RESOURCE OPTIMIZATION PROBLEMS USING REINFORCEMENT LEARNING

This page was built for publication: Pretty darn good control: when are approximate solutions better than approximate models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6077321)