Inverse Reinforcement Learning in Large State Spaces via Function Approximation
This work addresses scalability issues in inverse reinforcement learning, enabling applications in domains like medical rehabilitation for patients with spinal cord injuries.
The paper tackles the problem of inverse reinforcement learning in large state spaces by introducing a function approximation method that avoids solving expensive reinforcement learning problems, achieving higher accuracy and significantly better scalability than existing methods.
This paper introduces a new method for inverse reinforcement learning in large-scale and high-dimensional state spaces. To avoid solving the computationally expensive reinforcement learning problems in reward learning, we propose a function approximation method to ensure that the Bellman Optimality Equation always holds, and then estimate a function to maximize the likelihood of the observed motion. The time complexity of the proposed method is linearly proportional to the cardinality of the action set, thus it can handle large state spaces efficiently. We test the proposed method in a simulated environment, and show that it is more accurate than existing methods and significantly better in scalability. We also show that the proposed method can extend many existing methods to high-dimensional state spaces. We then apply the method to evaluating the effect of rehabilitative stimulations on patients with spinal cord injuries based on the observed patient motions.