paper-with-me

홈 › Papers

Cross-Domain Imitation Learning via Optimal Transport

2021-10-07 · ICLR 2022 4 · Arnaud Fickinger, samuel cohen, Stuart Russell, Brandon Amos

Cross-domain imitation learning studies how to leverage expert demonstrations of one agent to train an imitation agent with a different embodiment or morphology. Comparing trajectories and stationary distributions between the expert and imitation agents is challenging because they live on different systems that may not even have the same dimensionality. We propose Gromov-Wasserstein Imitation Learning (GWIL), a method for cross-domain imitation that uses the Gromov-Wasserstein distance to align and compare states between the different spaces of the agents. Our theory formally characterizes the scenarios where GWIL preserves optimality, revealing its possibilities and limitations. We demonstrate the effectiveness of GWIL in non-trivial continuous control domains ranging from simple rigid transformation of the expert domain to arbitrary transformation of the state-action space.

📄 PDF Abstract BibTeX arXiv:2110.03684

Code (1)

facebookresearch/gwil pytorch

Tasks

continuous-controlContinuous ControlImitation Learning

Similar Papers 제목 키워드 기반

MOST: Multi-Source Domain Adaptation via Optimal Transport for Student-Teacher Learning

2021-05-13 · UAI 2021 5 · Tuan Nguyen, Trung Le, He Zhao, Quan Hung Tran 외

Multi-source domain adaptation (DA) is more challenging than conventional DA because the knowledge is transferred from several source domains to a target domain. To this end, we propose in this paper a novel model for mu…

Domain AdaptationImitation LearningMulti-Source Unsupervised Domain AdaptationUnsupervised Domain Adaptation

Neural domain alignment for spoken language recognition based on optimal transport

2023-10-20 · Xugang Lu, Peng Shen, Yu Tsao, Hisashi Kawai

Domain shift poses a significant challenge in cross-domain spoken language recognition (SLR) by reducing its effectiveness. Unsupervised domain adaptation (UDA) algorithms have been explored to address domain shifts in S…

Domain AdaptationUnsupervised Domain Adaptation

Modeling User Preferences as Distributions for Optimal Transport-Based Cross-Domain Recommendation under Non-Overlapping Settings

2025-08-22 · Ziyin Xiao, Toyotaro Suzumura arxiv

Cross-domain recommender (CDR) systems aim to transfer knowledge from data-rich domains to data-sparse ones, alleviating sparsity and cold-start issues present in conventional single-domain recommenders. However, many CD…

InfoOT: Information Maximizing Optimal Transport

2022-10-06 · Ching-Yao Chuang, Stefanie Jegelka, David Alvarez-Melis

Optimal transport aligns samples across distributions by minimizing the transportation cost between them, e.g., the geometric distances. Yet, it ignores coherence structure in the data such as clusters, does not handle o…

Domain AdaptationRetrieval

Reliable Weighted Optimal Transport for Unsupervised Domain Adaptation

2020-06-01 · CVPR 2020 6 · Renjun Xu, Pelen Liu, Liyan Wang, Chao Chen 외

Recently, extensive researches have been proposed to address the UDA problem, which aims to learn transferrable models for the unlabeled target domain. Among them, the optimal transport is a promising metric to align the…

ClusteringDomain AdaptationUnsupervised Domain Adaptation