Stable Inverse Reinforcement Learning: Policies from Control Lyapunov Landscapes

TL;DR

This paper introduces a stable inverse reinforcement learning method that infers control Lyapunov functions from demonstrations, ensuring stability and efficiency in learning complex behaviors for autonomous systems.

Contribution

It reformulates IRL as a control Lyapunov function learning problem, providing stability guarantees and computational efficiency through convex optimization and closed-form policies.

Findings

Efficiently learns stable control policies from demonstrations.

Provides theoretical stability guarantees for the learned policies.

Validated on both simulated and real-world data.

Abstract

Learning from expert demonstrations to flexibly program an autonomous system with complex behaviors or to predict an agent's behavior is a powerful tool, especially in collaborative control settings. A common method to solve this problem is inverse reinforcement learning (IRL), where the observed agent, e.g., a human demonstrator, is assumed to behave according to the optimization of an intrinsic cost function that reflects its intent and informs its control actions. While the framework is expressive, it is also computationally demanding and generally lacks convergence guarantees. We therefore propose a novel, stability-certified IRL approach by reformulating the cost function inference problem to learning control Lyapunov functions (CLF) from demonstrations data. By additionally exploiting closed-form expressions for associated control policies, we are able to efficiently search the space of CLFs by observing the attractor landscape of the induced dynamics. For the construction of the inverse optimal CLFs, we use a Sum of Squares and formulate a convex optimization problem. We present a theoretical analysis of the optimality properties provided by the CLF and evaluate our approach using both simulated and real-world data.