Safe and Efficient Reinforcement Learning Using Disturbance-Observer-Based Control Barrier Functions

no code implementations • 30 Nov 2022 • Yikun Cheng, Pan Zhao, Naira Hovakimyan

Safety filters, e. g., based on control barrier functions (CBFs), provide a promising way for safe RL via modifying the unsafe actions of an RL agent on the fly.

Computational Efficiency Efficient Exploration +4

Robustifying Reinforcement Learning Policies with $\mathcal{L}_1$ Adaptive Control

no code implementations • 4 Jun 2021 • Yikun Cheng, Pan Zhao, Manan Gandhi, Bo Li, Evangelos Theodorou, Naira Hovakimyan

A reinforcement learning (RL) policy trained in a nominal environment could fail in a new/perturbed environment due to the existence of dynamic variations.

reinforcement-learning Reinforcement Learning (RL)