DIDA: Denoised Imitation Learning based on Domain Adaptation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Huang, Kaichen, Sun, Hai-Hang, Wan, Shenghua, Shao, Minghao, Feng, Shuai, Gan, Le, Zhan, De-Chuan
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914741139537920
author Huang, Kaichen
Sun, Hai-Hang
Wan, Shenghua
Shao, Minghao
Feng, Shuai
Gan, Le
Zhan, De-Chuan
author_facet Huang, Kaichen
Sun, Hai-Hang
Wan, Shenghua
Shao, Minghao
Feng, Shuai
Gan, Le
Zhan, De-Chuan
contents Imitating skills from low-quality datasets, such as sub-optimal demonstrations and observations with distractors, is common in real-world applications. In this work, we focus on the problem of Learning from Noisy Demonstrations (LND), where the imitator is required to learn from data with noise that often occurs during the processes of data collection or transmission. Previous IL methods improve the robustness of learned policies by injecting an adversarially learned Gaussian noise into pure expert data or utilizing additional ranking information, but they may fail in the LND setting. To alleviate the above problems, we propose Denoised Imitation learning based on Domain Adaptation (DIDA), which designs two discriminators to distinguish the noise level and expertise level of data, facilitating a feature encoder to learn task-related but domain-agnostic representations. Experiment results on MuJoCo demonstrate that DIDA can successfully handle challenging imitation tasks from demonstrations with various types of noise, outperforming most baseline methods.
format Preprint
id arxiv_https___arxiv_org_abs_2404_03382
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DIDA: Denoised Imitation Learning based on Domain Adaptation
Huang, Kaichen
Sun, Hai-Hang
Wan, Shenghua
Shao, Minghao
Feng, Shuai
Gan, Le
Zhan, De-Chuan
Machine Learning
Artificial Intelligence
Imitating skills from low-quality datasets, such as sub-optimal demonstrations and observations with distractors, is common in real-world applications. In this work, we focus on the problem of Learning from Noisy Demonstrations (LND), where the imitator is required to learn from data with noise that often occurs during the processes of data collection or transmission. Previous IL methods improve the robustness of learned policies by injecting an adversarially learned Gaussian noise into pure expert data or utilizing additional ranking information, but they may fail in the LND setting. To alleviate the above problems, we propose Denoised Imitation learning based on Domain Adaptation (DIDA), which designs two discriminators to distinguish the noise level and expertise level of data, facilitating a feature encoder to learn task-related but domain-agnostic representations. Experiment results on MuJoCo demonstrate that DIDA can successfully handle challenging imitation tasks from demonstrations with various types of noise, outperforming most baseline methods.
title DIDA: Denoised Imitation Learning based on Domain Adaptation
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2404.03382