相关论文: Cross-Domain Imitation Learning with a Dual Struct…

It is significantly challenging to recognize daily human actions in homes due to the diversity and dynamic changes in unconstrained home environments. It spurs the need to continually adapt to various users and scenes. Fine-tuning current…

Imitation learning (IL) aims to learn an optimal policy from demonstrations. However, such demonstrations are often imperfect since collecting optimal ones is costly. To effectively learn from imperfect demonstrations, we propose a novel…

Unsupervised domain adaptation person re-identification (Re-ID) aims to identify pedestrian images within an unlabeled target domain with an auxiliary labeled source-domain dataset. Many existing works attempt to recover reliable identity…

Diffusion models excel at generative modeling (e.g., text-to-image) but sampling requires multiple denoising network passes, limiting practicality. Efforts such as progressive distillation or consistency distillation have shown promise by…

Transferring knowledge in cross-domain reinforcement learning is a challenging setting in which learning is accelerated by reusing knowledge from a task with different observation and/or action space. However, it is often necessary to…

Domain-Incremental Learning (DIL) focuses on continual learning in non-stationary environments, requiring models to adjust to evolving domains while preserving historical knowledge. DIL faces two critical challenges in the context of…

The goal of imitation learning is to mimic expert behavior without access to an explicit reward signal. Expert demonstrations provided by humans, however, often show significant variability due to latent factors that are typically not…

With the proliferation of social media platforms and e-commerce sites, several cross-domain collaborative filtering strategies have been recently introduced to transfer the knowledge of user preferences across domains. The main challenge of…

Following the impressive capabilities of in-context learning with large transformers, In-Context Imitation Learning (ICIL) is a promising opportunity for robotics. We introduce Instant Policy, which learns new tasks instantly (without…

Learning to perform tasks by leveraging a dataset of expert observations, also known as imitation learning from observations (ILO), is an important paradigm for learning skills without access to the expert reward function or the expert…

Imitation learning (IL) consists of a set of tools that leverage expert demonstrations to quickly learn policies. However, if the expert is suboptimal, IL can yield policies with inferior performance compared to reinforcement learning (RL).…

Existing unsupervised domain adaptation methods aim to transfer knowledge from a label-rich source domain to an unlabeled target domain. However, obtaining labels for some source domains may be very expensive, making complete labeling as…

In this work we describe a novel deep reinforcement learning architecture that allows multiple actions to be selected at every time-step in an efficient manner. Multi-action policies allow complex behaviours to be learnt that would…

We show that a critical vulnerability in adversarial imitation is the tendency of discriminator networks to learn spurious associations between visual features and expert labels. When the discriminator focuses on task-irrelevant features,…

How do the neural networks distinguish two images? It is of critical importance to understand the matching mechanism of deep models for developing reliable intelligent systems for many risky visual applications such as surveillance and…

Domain incremental learning aims to adapt to a sequence of domains with access to only a small subset of data (i.e., memory) from previous domains. Various methods have been proposed for this problem, but it is still unclear how they are…

We investigate the visual cross-embodiment imitation setting, in which agents learn policies from videos of other agents (such as humans) demonstrating the same task, but with stark differences in their embodiments -- shape, actions,…

Recent advances in domain adaptation reveal that adversarial learning on deep neural networks can learn domain invariant features to reduce the shift between source and target domains. While such adversarial approaches achieve domain-level…

Developing agents that can perform challenging complex tasks is the goal of reinforcement learning. The model-free reinforcement learning has been considered as a feasible solution. However, the state of the art research has been to develop…

Cross domain recommender system constitutes a powerful method to tackle the cold-start and sparsity problem by aggregating and transferring user preferences across multiple category domains. Therefore, it has great potential to improve…