Control-Tutored Reinforcement Learning: Towards the Integration of Data-Driven and Model-Based Control
This work addresses data efficiency in reinforcement learning for control tasks, presenting an incremental integration of model-based and data-driven methods.
The authors tackled the problem of improving data efficiency in reinforcement learning by integrating a feedback controller derived from an approximate model to assist the learning process, resulting in the development of Control-Tutored Q-learning (CTQL) and its probabilistic variant (pCTQL), which were validated and benchmarked against Q-Learning on an inverted pendulum stabilization task in OpenAI Gym.
We present an architecture where a feedback controller derived on an approximate model of the environment assists the learning process to enhance its data efficiency. This architecture, which we term as Control-Tutored Q-learning (CTQL), is presented in two alternative flavours. The former is based on defining the reward function so that a Boolean condition can be used to determine when the control tutor policy is adopted, while the latter, termed as probabilistic CTQL (pCTQL), is instead based on executing calls to the tutor with a certain probability during learning. Both approaches are validated, and thoroughly benchmarked against Q-Learning, by considering the stabilization of an inverted pendulum as defined in OpenAI Gym as a representative problem.