Pilot Performance modeling via observer-based inverse reinforcement learning

no code implementations • 24 Jul 2023 • Jared Town, Zachary Morrison, Rushikesh Kamalapurkar

The observer is shown to converge to one of the equivalent solutions of the IRL problem.

reinforcement-learning

Nonuniqueness and Convergence to Equivalent Solutions in Observer-based Inverse Reinforcement Learning

no code implementations • 28 Oct 2022 • Jared Town, Zachary Morrison, Rushikesh Kamalapurkar

A key challenge in solving the deterministic inverse reinforcement learning (IRL) problem online and in real-time is the existence of multiple solutions.

reinforcement-learning Reinforcement Learning (RL)