Efficient model-based reinforcement learning for approximate online optimal control

DOI10.1016/j.automatica.2016.08.004zbMath1348.93167arXiv1502.02609OpenAlexW1540245649MaRDI QIDQ340682

Joel A. Rosenfeld, Rushikesh Kamalapurkar, Warren E. Dixon

Publication date: 14 November 2016

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1502.02609

zbMATH Keywords

adaptive controllocal approximationdata-based controlmodel-based reinforcement learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Applications of optimal control and differential games (49N90) Adaptive control/observation systems (93C40)

Related Items

Approximate optimal influence over an agent through an uncertain interaction dynamic, Temporal logic guided safe model-based reinforcement learning: a hybrid systems approach, Reinforcement learning for adaptive optimal control of continuous-time linear periodic systems, Two‐loop reinforcement learning algorithm for finite‐horizon optimal control of continuous‐time affine nonlinear systems, Model-based reinforcement learning for approximate optimal control with temporal logic specifications, Data-based reinforcement learning approximate optimal control for an uncertain nonlinear system with control effectiveness faults, Mixed density methods for approximate dynamic programming, A hybrid dynamical systems perspective on reinforcement learning for cyber-physical systems: vistas, open problems, and challenges, Safe exploration in model-based reinforcement learning using control barrier functions

Uses Software

• PILCO

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Optimal control of unknown affine nonlinear discrete-time systems using offline-trained neural networks with proof of convergence
• Integral reinforcement learning and experience replay for adaptive optimal control of partially-unknown constrained-input continuous-time systems
• Reinforcement \(Q\)-learning for optimal tracking control of linear discrete-time systems with unknown dynamics
• Adaptive dynamic programming and optimal control of nonlinear nonaffine systems
• Adaptive dynamic programming for control. Algorithms and stability
• A single network adaptive critic (SNAC) architecture for optimal control synthesis for a class of nonlinear systems
• Model-based reinforcement learning for approximate optimal regulation
• Online actor-critic algorithm to solve the continuous-time infinite horizon optimal control problem
• A novel actor-critic-identifier architecture for approximate optimal control of uncertain nonlinear systems
• Data-based approximate policy iteration for affine nonlinear continuous-time optimal control design
• Optimal control of unknown nonaffine nonlinear discrete-time systems based on adaptive dynamic programming
• Concurrent learning adaptive control of linear systems with exponentially convergent bounds
• Neural-network-observer-based optimal control for unknown nonlinear systems using adaptive dynamic programming
• Direct adaptive control for a class of discrete‐time unknown nonaffine nonlinear systems using neural networks
• Support Vector Machines
• Algorithms for Reinforcement Learning
• Robust adaptive LQ control schemes
• OnActor-Critic Algorithms
• Reinforcement learning for adaptive optimal control of unknown continuous-time nonlinear systems with input constraints