End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks
This addresses the safety-critical issue in real-world RL applications, such as robotics and autonomous vehicles, by providing a framework that prevents system failures during learning, though it builds incrementally on existing CBF and RL techniques.
The paper tackles the problem of ensuring safety during reinforcement learning for continuous control tasks by proposing a controller architecture that combines model-free RL, model-based control barrier functions, and online learning of system dynamics. The result is a method that guarantees safety with high probability, demonstrates greater policy exploration efficiency, and achieves much greater sample efficiency in learning compared to state-of-the-art algorithms.
Reinforcement Learning (RL) algorithms have found limited success beyond simulated applications, and one main reason is the absence of safety guarantees during the learning process. Real world systems would realistically fail or break before an optimal controller can be learned. To address this issue, we propose a controller architecture that combines (1) a model-free RL-based controller with (2) model-based controllers utilizing control barrier functions (CBFs) and (3) on-line learning of the unknown system dynamics, in order to ensure safety during learning. Our general framework leverages the success of RL algorithms to learn high-performance controllers, while the CBF-based controllers both guarantee safety and guide the learning process by constraining the set of explorable polices. We utilize Gaussian Processes (GPs) to model the system dynamics and its uncertainties. Our novel controller synthesis algorithm, RL-CBF, guarantees safety with high probability during the learning process, regardless of the RL algorithm used, and demonstrates greater policy exploration efficiency. We test our algorithm on (1) control of an inverted pendulum and (2) autonomous car-following with wireless vehicle-to-vehicle communication, and show that our algorithm attains much greater sample efficiency in learning than other state-of-the-art algorithms and maintains safety during the entire learning process.