Increasing Information for Model Predictive Control with Semi-Markov Decision Processes
This work addresses a bottleneck in model predictive control for dynamical systems, offering an incremental improvement in sample efficiency.
The paper tackles the limitation of sequential exploration in Learning-Based Model Predictive Control by introducing temporal abstraction with Semi-Markov Decision Processes, resulting in increased information from gathered data and reduced sample complexity.
Recent works in Learning-Based Model Predictive Control of dynamical systems show impressive sample complexity performances using criteria from Information Theory to accelerate the learning procedure. However, the sequential exploration opportunities are limited by the system local state, restraining the amount of information of the observations from the current exploration trajectory. This article resolves this limitation by introducing temporal abstraction through the framework of Semi-Markov Decision Processes. The framework increases the total information of the gathered data for a fixed sampling budget, thus reducing the sample complexity.