Model-based inverse reinforcement learning for deterministic systems

DOI10.1016/J.AUTOMATICA.2022.110242zbMath1485.93135OpenAlexW4221041364MaRDI QIDQ2125544

Moad Abudia, S. M. Nahid Mahmud, Ryan Self, Rushikesh Kamalapurkar

Publication date: 14 April 2022

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.automatica.2022.110242

zbMATH Keywords

system identificationstate estimationinverse optimal controlinverse reinforcement learning

Mathematics Subject Classification ID

System identification (93B30) Inverse problems in optimal control (49N45)

Related Items (2)

Off-policy inverse Q-learning for discrete-time antagonistic unknown systems ⋮ Global inverse optimality for a class of recurrent neural networks with multiple proportional delays

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Partial differential equations 1. Foundations and integral representations. With consideration of lectures by E. Heinz.
• Finite-horizon inverse optimal control for discrete-time nonlinear systems
• Online inverse optimal control for control-constrained discrete-time systems on finite and infinite horizons
• Approximate optimal trajectory tracking for continuous-time nonlinear systems
• Concurrent learning adaptive control of linear systems with exponentially convergent bounds
• On the Uniform Asymptotic Stability of Certain Linear Nonautonomous Differential Equations
• Infinite Time Horizon Maximum Causal Entropy Inverse Reinforcement Learning
• Adaptive observers with arbitrary exponential rate of convergence for nonlinear systems
• Finite-Time Parameter Estimation in Adaptive Control of Nonlinear Systems
• Kernel-Based Simultaneous Parameter-State Estimation for Continuous-Time Systems

This page was built for publication: Model-based inverse reinforcement learning for deterministic systems