Control-Tutored Reinforcement Learning
This work addresses the challenge of slow learning and inefficient exploration in reinforcement learning for multi-agent control tasks, representing an incremental improvement by integrating model-based tutoring into tabular methods.
The authors tackled the problem of improving exploration and reducing learning times in reinforcement learning by introducing a control-tutored reinforcement learning (CTRL) algorithm that leverages limited knowledge from a model-based control strategy, demonstrating its effectiveness in herding and containing free-roving agents in a plane.
We introduce a control-tutored reinforcement learning (CTRL) algorithm. The idea is to enhance tabular learning algorithms so as to improve the exploration of the state-space, and substantially reduce learning times by leveraging some limited knowledge of the plant encoded into a tutoring model-based control strategy. We illustrate the benefits of our novel approach and its effectiveness by using the problem of controlling one or more agents to herd and contain within a goal region a set of target free-roving agents in the plane.