Online Observer-Based Inverse Reinforcement Learning

Abstract

In this paper, a novel approach to the output-feedback inverse reinforcement learning (IRL) problem is developed by casting the IRL problem, for linear systems with quadratic cost functions, as a state estimation problem. Two observer-based techniques for IRL are developed, including a novel observer method that re-uses previous state estimates via history stacks. Theoretical guarantees for convergence and robustness are established under appropriate excitation conditions. Simulations demonstrate the performance of the developed observers and filters under noisy and noise-free measurements.

arXiv comment7 pages, 3 figures

References in corpus (8)

• Maximum Entropy Deep Inverse Reinforcement Learning
• Inverse Reinforcement Learning in Swarm Systems
• Online Observer-Based Inverse Reinforcement Learning
• Online inverse reinforcement learning with unknown disturbances
• Online Simultaneous State and Parameter Estimation for Second-order Nonlinear Systems
• Competitive Multi-agent Inverse Reinforcement Learning with Sub-optimal Demonstrations
• Inverse reinforcement learning in continuous time and space
• Online Output-Feedback Parameter and State Estimation for Second Order Linear Systems

Cited by in corpus (1)

• Online Observer-Based Inverse Reinforcement Learning