Stable Inverse Reinforcement Learning: Policies from Control Lyapunov Landscapes

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Tesfazgi, Samuel, Sprandl, Leonhard, Lederer, Armin, Hirche, Sandra
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916246150184960
author Tesfazgi, Samuel
Sprandl, Leonhard
Lederer, Armin
Hirche, Sandra
author_facet Tesfazgi, Samuel
Sprandl, Leonhard
Lederer, Armin
Hirche, Sandra
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_08756
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Stable Inverse Reinforcement Learning: Policies from Control Lyapunov Landscapes
Tesfazgi, Samuel
Sprandl, Leonhard
Lederer, Armin
Hirche, Sandra
Systems and Control
Machine Learning
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.
title Stable Inverse Reinforcement Learning: Policies from Control Lyapunov Landscapes
topic Systems and Control
Machine Learning
url https://arxiv.org/abs/2405.08756