Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Town, Jared, Morrison, Zachary, Kamalapurkar, Rushikesh
Format: Preprint
Veröffentlicht: 2022
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2210.16299
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910463207407616
author Town, Jared
Morrison, Zachary
Kamalapurkar, Rushikesh
author_facet Town, Jared
Morrison, Zachary
Kamalapurkar, Rushikesh
contents A key challenge in solving the deterministic inverse reinforcement learning (IRL) problem online and in real-time is the existence of multiple solutions. Nonuniqueness necessitates the study of the notion of equivalent solutions, i.e., solutions that result in a different cost functional but same feedback matrix, and convergence to such solutions. While offline algorithms that result in convergence to equivalent solutions have been developed in the literature, online, real-time techniques that address nonuniqueness are not available. In this paper, a regularized history stack observer that converges to approximately equivalent solutions of the IRL problem is developed. Novel data-richness conditions are developed to facilitate the analysis and simulation results are provided to demonstrate the effectiveness of the developed technique.
format Preprint
id arxiv_https___arxiv_org_abs_2210_16299
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Nonuniqueness and Convergence to Equivalent Solutions in Observer-based Inverse Reinforcement Learning
Town, Jared
Morrison, Zachary
Kamalapurkar, Rushikesh
Systems and Control
Machine Learning
A key challenge in solving the deterministic inverse reinforcement learning (IRL) problem online and in real-time is the existence of multiple solutions. Nonuniqueness necessitates the study of the notion of equivalent solutions, i.e., solutions that result in a different cost functional but same feedback matrix, and convergence to such solutions. While offline algorithms that result in convergence to equivalent solutions have been developed in the literature, online, real-time techniques that address nonuniqueness are not available. In this paper, a regularized history stack observer that converges to approximately equivalent solutions of the IRL problem is developed. Novel data-richness conditions are developed to facilitate the analysis and simulation results are provided to demonstrate the effectiveness of the developed technique.
title Nonuniqueness and Convergence to Equivalent Solutions in Observer-based Inverse Reinforcement Learning
topic Systems and Control
Machine Learning
url https://arxiv.org/abs/2210.16299