Bellman's principle of optimality and deep reinforcement learning for time-varying tasks

DOI10.1080/00207179.2021.1913516MaRDI QIDQ5043501zbMATHOpenAlexFDO

Authors Alessandro Giuseppi, Antonio Pietrabissa

Publication date 6 October 2022

Published in International Journal of Control (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1080/00207179.2021.1913516

zbMATH Keywords

finite-horizon optimal controlBellman's principlemodel-free controldeep reinforcement learning

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40) Optimal stochastic control (93E20)

Recommendations

• Reinforcement Learning and Stochastic Optimization
• The Bellman's principle of optimality in the discounted dynamic programming
• From reinforcement learning to optimal control: a unified framework for sequential decisions
• Time-varying policy rule under learning
• Approximate dynamic programming via iterated Bellman inequalities
• Policy iterations for reinforcement learning problems in continuous time and space -- fundamental theory and methods

Cites work

• scientific article; zbMATH DE number 700091 (Why is no real title available?)
• Adaptive dynamic programming for discrete-time linear quadratic regulation based on multirate generalised policy iteration
• Allocating resources via price management systems: a dynamic programming-based approach
• An iterative adaptive dynamic programming method for solving a class of nonlinear zero-sum differential games
• Dynamic programming and optimal control. Vol. 1.
• Modelling and solving resource allocation problems via a dynamic programming approach
• Multi-objective reinforcement learning using sets of Pareto dominating policies
• Reinforcement learning. An introduction

Cited in

(2)

• A Lyapunov-based version of the value iteration algorithm formulated as a discrete-time switched affine system
• Time-varying policy rule under learning

Describes a project that uses

Uses Software

• OpenAI Gym
• PyTorch
• GitHub

This page was built for publication: Bellman's principle of optimality and deep reinforcement learning for time-varying tasks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5043501)