Cross-Domain Imitation Learning via Optimal Transport
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.
Code (1)
Tasks
continuous-controlContinuous ControlImitation LearningSimilar Papers 제목 키워드 기반
MOST: Multi-Source Domain Adaptation via Optimal Transport for Student-Teacher Learning
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 AdaptationNeural domain alignment for spoken language recognition based on optimal transport
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 AdaptationModeling User Preferences as Distributions for Optimal Transport-Based Cross-Domain Recommendation under Non-Overlapping Settings
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
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 AdaptationRetrievalReliable Weighted Optimal Transport for Unsupervised Domain Adaptation
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