A model for system uncertainty in reinforcement learning

DOI10.1016/J.SYSCONLE.2018.09.011zbMath1408.93078arXiv1802.07668OpenAlexW2963796363MaRDI QIDQ1729066

Michele Palladino, Ryan W. Murray

Publication date: 27 February 2019

Published in: Systems \& Control Letters (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1802.07668

zbMATH Keywords

dynamic programmingadaptive controlmachine learninglearning systems

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Control/observation systems with incomplete information (93C41) Adaptive control/observation systems (93C40) Dynamic programming (90C39) Stochastic systems in control theory (general) (93E03) Optimality conditions for problems involving ordinary differential equations (49K15)

Related Items (5)

A new algorithm for the LQR problem with partially unknown dynamics ⋮ Optimal control of ensembles of dynamical systems ⋮ Convergence results for an averaged LQR problem with applications to reinforcement learning ⋮ Data-driven fault-tolerant formation control for nonlinear quadrotors under multiple simultaneous actuator faults ⋮ Learning for MPC with stability \& safety guarantees

Uses Software

• PILCO

Cites Work

• Unnamed Item
• Integral reinforcement learning and experience replay for adaptive optimal control of partially-unknown constrained-input continuous-time systems
• Necessary conditions for adverse control problems expressed by relaxed derivatives
• Dual-control theory. I
• Model-based reinforcement learning for approximate optimal regulation
• A study of reinfrocement learning in the continuous case by the means of viscosity solutions
• Necessary optimality conditions for average cost minimization problems
• Convex Optimization: Algorithms and Complexity
• Dual Control for Approximate Bayesian Reinforcement Learning
• Online Adaptive Optimal Control Based on Reinforcement Learning
• Nonsmooth Problems with Conflicting Controls
• Robust maximum principle in minimax control
• Minimax Optimal Control
• Optimal control and viscosity solutions of Hamilton-Jacobi-Bellman equations
• \(H^ \infty\)-optimal control and related minimax design problems. A dynamic game approach.

This page was built for publication: A model for system uncertainty in reinforcement learning