Domain-Robust Visual Imitation Learning with Mutual Information Constraints
Human beings are able to understand objectives and learn by simply observing others perform a task. Imitation learning methods aim to replicate such capabilities, however, they generally depend on access to a full set of optimal states and actions taken with the agent's actuators and from the agent's point of view. In this paper, we introduce a new algorithm - called Disentangling Generative Adversarial Imitation Learning (DisentanGAIL) - with the purpose of bypassing such constraints. Our algorithm enables autonomous agents to learn directly from high dimensional observations of an expert performing a task, by making use of adversarial learning with a latent representation inside the discriminator network. Such latent representation is regularized through mutual information constraints to incentivize learning only features that encode information about the completion levels of the task being demonstrated. This allows to obtain a shared feature space to successfully perform imitation while disregarding the differences between the expert's and the agent's domains. Empirically, our algorithm is able to efficiently imitate in a diverse range of control problems including balancing, manipulation and locomotive tasks, while being robust to various domain differences in terms of both environment appearance and agent embodiment.
Code (1)
Tasks
Imitation LearningSimilar Papers 제목 키워드 기반
Self-Supervised Representation Learning From Multi-Domain Data
We present an information-theoretically motivated constraint for self-supervised representation learning from multiple related domains. In contrast to previous self-supervised learning methods, our approach learns from m…
Representation LearningSelf-Supervised LearningTransfer LearningMCMI: Multi-Cycle Image Translation with Mutual Information Constraints
We present a mutual information-based framework for unsupervised image-to-image translation. Our MCMI approach treats single-cycle image translation models as modules that can be used recurrently in a multi-cycle transla…
Image-to-Image TranslationTranslationUnsupervised Image-To-Image TranslationTubeRMC: Tube-conditioned Reconstruction with Mutual Constraints for Weakly-supervised Spatio-Temporal Video Grounding
Spatio-Temporal Video Grounding (STVG) aims to localize a spatio-temporal tube that corresponds to a given language query in an untrimmed video. This is a challenging task since it involves complex vision-language unders…
Spatio-Temporal Video GroundingVisual GroundingBoosting Cross-spectral Unsupervised Domain Adaptation for Thermal Semantic Segmentation
In autonomous driving, thermal image semantic segmentation has emerged as a critical research area, owing to its ability to provide robust scene understanding under adverse visual conditions. In particular, unsupervised …
Autonomous DrivingDomain AdaptationImage SegmentationScene Understanding+4Information-Theoretic Constraints for Continual Vision-Language-Action Alignment
When deployed in open-ended robotic environments, Vision--Language--Action (VLA) models need to continually acquire new skills, yet suffer from severe catastrophic forgetting. We observe that this degradation is related …
Contrastive LearningContinual Learning