Stabilizing Neural Control Using Self-Learned Almost Lyapunov Critics
arXiv:2107.04989
Abstract
The lack of stability guarantee restricts the practical use of learning-based methods in core control problems in robotics. We develop new methods for learning neural control policies and neural Lyapunov critic functions in the model-free reinforcement learning (RL) setting. We use sample-based approaches and the Almost Lyapunov function conditions to estimate the region of attraction and invariance properties through the learned Lyapunov critic functions. The methods enhance stability of neural controllers for various nonlinear systems including automobile and quadrotor control.
arXiv commentICRA 2021
References in corpus (7)
- Trust Region Policy Optimization
- Safe Model-based Reinforcement Learning with Stability Guarantees
- Lyapunov-based Safe Policy Optimization for Continuous Control
- Neural Lyapunov Control
- The Lyapunov Neural Network: Adaptive Stability Certification for Safe Learning of Dynamical Systems
- Control Regularization for Reduced Variance Reinforcement Learning
- Safe Interactive Model-Based Learning