2022/07/29 by Wenhao Luo, Wen Sun, Luo, Wenhao +3 · 1 citation
Computer Science · Decision Sciences · Engineering · Physics and Astronomy · #Advanced Bandit Algorithms Research #Advanced Control Systems Optimization #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Model Reduction and Neural Networks #Robotics (cs.RO) #Systems and Control (eess.SY) #cs.LG #cs.RO #cs.SY #eess.SY #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2207.14419
The 15th International Workshop on the Algorithmic Foundations of Robotics (WAFR 2022)
arxiv created 2022/07/29 · openalex publication_date 2022/07/29 · arxiv updated 2022/08/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Reinforcement Learning (RL) and continuous nonlinear control have been successfully deployed in multiple domains of complicated sequential decision-making tasks. However, given the exploration nature of the learning process and the presence of model uncertainty, it is challenging to apply them to safety-critical control tasks due to the lack of safety guarantee. On the other hand, while combining control-theoretical approaches with learning algorithms has shown promise in safe RL applications, the sample efficiency of safe data collection process for control is not well addressed. In this paper, we propose a provably sample efficient episodic safe learning framework for online control tasks that leverages safe exploration and exploitation in an unknown, nonlinear dynamical system. In particular, the framework 1) extends control barrier functions (CBFs) in a stochastic setting to achieve provable high-probability safety under uncertainty during model learning and 2) integrates an optimism-based exploration strategy to efficiently guide the safe exploration process with learned dynamics for near optimal control performance. We provide formal analysis on the episodic regret bound against the optimal controller and probabilistic safety with theoretical guarantees. Simulation results are provided to demonstrate the effectiveness and efficiency of the proposed algorithm.