相关论文: Domain Adversarial Reinforcement Learning

Adversarial discriminative domain adaptation (ADDA) is an efficient framework for unsupervised domain adaptation in image classification, where the source and target domains are assumed to have the same classes, but no labels are available…

To be successful in single source domain generalization, maximizing diversity of synthesized domains has emerged as one of the most effective strategies. Many of the recent successes have come from methods that pre-specify the types of…

In this paper, we consider domain-adaptive imitation learning with visual observation, where an agent in a target domain learns to perform a task by observing expert demonstrations in a source domain. Domain adaptive imitation learning…

Collecting well-annotated image datasets to train modern machine learning algorithms is prohibitively expensive for many tasks. One appealing alternative is rendering synthetic data where ground-truth annotations are generated…

Due to the numerous potential applications in visual surveillance and nighttime driving, recognizing human action in low-light conditions remains a difficult problem in computer vision. Existing methods separate action recognition and dark…

In this paper, hypernetworks are trained to generate behaviors across a range of unseen task conditions, via a novel TD-based training objective and data from a set of near-optimal RL solutions for training tasks. This work relates to meta…

This paper addresses the issue of generalization for Semantic Parsing in an adversarial framework. Building models that are more robust to inter-document variability is crucial for the integration of Semantic Parsing technologies in real…

Designing reward functions that generalize beyond controlled laboratory settings remains a fundamental challenge in reinforcement learning for robotics. In open-world manipulation problems, a single task can appear in numerous variants…

Discrepancy between training and testing domains is a fundamental problem in the generalization of machine learning techniques. Recently, several approaches have been proposed to learn domain invariant feature representations through…

Recently, there are many efforts attempting to learn useful policies for continuous control in visual reinforcement learning (RL). In this scenario, it is important to learn a generalizable policy, as the testing environment may differ from…

While domain adaptation has been actively researched in recent years, most theoretical results and algorithms focus on the single-source-single-target adaptation setting. Naive application of such algorithms on multiple source domain…

We introduce a new representation learning algorithm suited to the context of domain adaptation, in which data at training and test time come from similar but different distributions. Our algorithm is directly inspired by theory on domain…

Reinforcement post training (RPT) has recently shown promise in improving the reasoning abilities of large language models (LLMs). However, it remains unclear how well these improvements generalize to new domains, as prior work evaluates…

We study the problem of representation transfer in offline Reinforcement Learning (RL), where a learner has access to episodic data from a number of source tasks collected a priori, and aims to learn a shared representation to be used in…

In the problem of domain generalization (DG), there are labeled training data sets from several related prediction problems, and the goal is to make accurate predictions on future unlabeled data sets that are not known to the learner. This…

In recent years, by leveraging more data, computation, and diverse tasks, learned optimizers have achieved remarkable success in supervised learning, outperforming classical hand-designed optimizers. Reinforcement learning (RL) is…

Deep reinforcement learning is poised to revolutionise the field of AI and represents a step towards building autonomous systems with a higher level understanding of the visual world. Currently, deep learning is enabling reinforcement…

In practical applications, we can rarely assume full observability of a system's environment, despite such knowledge being important for determining a reactive control system's precise interaction with its environment. Therefore, we propose…

Traditional deep learning algorithms often fail to generalize when they are tested outside of the domain of the training data. The issue can be mitigated by using unlabeled data from the target domain at training time, but because data…

Controlling artificial agents from visual sensory data is an arduous task. Reinforcement learning (RL) algorithms can succeed but require large amounts of interactions between the agent and the environment. To alleviate the issue,…