Critic as Lyapunov function (CALF): a model-free, stability-ensuring agent

TL;DR

CALF is a novel model-free reinforcement learning agent that guarantees environment stability during learning, significantly improving performance in a mobile robot simulation compared to traditional methods.

Contribution

The paper introduces CALF, a new reinforcement learning agent that ensures online stability without relying on models, bridging classical control and RL.

Findings

CALF outperforms SARSA-m in stabilizing the environment.

CALF improves nominal stabilizer performance.

Demonstrated success in mobile robot simulation.

Abstract

This work presents and showcases a novel reinforcement learning agent called Critic As Lyapunov Function (CALF) which is model-free and ensures online environment, in other words, dynamical system stabilization. Online means that in each learning episode, the said environment is stabilized. This, as demonstrated in a case study with a mobile robot simulator, greatly improves the overall learning performance. The base actor-critic scheme of CALF is analogous to SARSA. The latter did not show any success in reaching the target in our studies. However, a modified version thereof, called SARSA-m here, did succeed in some learning scenarios. Still, CALF greatly outperformed the said approach. CALF was also demonstrated to improve a nominal stabilizer provided to it. In summary, the presented agent may be considered a viable approach to fusing classical control with reinforcement learning. Its concurrent approaches are mostly either offline or model-based, like, for instance, those that fuse model-predictive control into the agent.