Stability-certified reinforcement learning: A control-theoretic perspective

10/26/2018
by   Ming Jin, et al.
0

We investigate the important problem of certifying stability of reinforcement learning policies when interconnected with nonlinear dynamical systems. We show that by regulating the input-output gradients of policies, strong guarantees of robust stability can be obtained based on a proposed semidefinite programming feasibility problem. The method is able to certify a large set of stabilizing controllers by exploiting problem-specific structures; furthermore, we analyze and establish its (non)conservatism. Empirical evaluations on two decentralized control tasks, namely multi-flight formation and power system frequency regulation, demonstrate that the reinforcement learning agents can have high performance within the stability-certified parameter space, and also exhibit stable learning behaviors in the long run.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/23/2017

Safe Model-based Reinforcement Learning with Stability Guarantees

Reinforcement learning is a powerful paradigm for learning optimal polic...
research
06/06/2020

Automatic Policy Synthesis to Improve the Safety of Nonlinear Dynamical Systems

Learning controllers merely based on a performance metric has been prove...
research
02/22/2022

A Benchmark Comparison of Learned Control Policies for Agile Quadrotor Flight

Quadrotors are highly nonlinear dynamical systems that require carefully...
research
12/14/2020

Safe Reinforcement Learning with Stability Safety Guarantees Using Robust MPC

Reinforcement Learning offers tools to optimize policies based on the da...
research
04/07/2023

A modular framework for stabilizing deep reinforcement learning control

We propose a framework for the design of feedback controllers that combi...
research
03/22/2022

Review of Metrics to Measure the Stability, Robustness and Resilience of Reinforcement Learning

Reinforcement learning has received significant interest in recent years...
research
07/03/2019

Safe Approximate Dynamic Programming Via Kernelized Lipschitz Estimation

We develop a method for obtaining safe initial policies for reinforcemen...

Please sign up or login with your details

Forgot password? Click here to reset