A Function Approximation Method for Model-based High-Dimensional Inverse Reinforcement Learning
This work addresses the problem of efficient inverse reinforcement learning for high-dimensional applications, such as clinical assessment, but is incremental as it builds on existing model-based methods with a focus on computational improvements.
The paper tackles the computational challenge of inverse reinforcement learning in high-dimensional state spaces by proposing a function approximation method that ensures the Bellman Optimality Equation holds, achieving linear time complexity relative to the action set size. It demonstrates accuracy in simulations and applicability in clinical tasks for evaluating doctor proficiency.
This works handles the inverse reinforcement learning problem in high-dimensional state spaces, which relies on an efficient solution of model-based high-dimensional reinforcement learning problems. To solve the computationally expensive reinforcement learning problems, we propose a function approximation method to ensure that the Bellman Optimality Equation always holds, and then estimate a function based on the observed human actions for inverse reinforcement learning problems. The time complexity of the proposed method is linearly proportional to the cardinality of the action set, thus it can handle high-dimensional even continuous state spaces efficiently. We test the proposed method in a simulated environment to show its accuracy, and three clinical tasks to show how it can be used to evaluate a doctor's proficiency.