Related papers: Domain Adversarial Reinforcement Learning
A fundamental trait of intelligence is the ability to achieve goals in the face of novel circumstances, such as making decisions from new action choices. However, standard reinforcement learning assumes a fixed set of actions and requires…
Recent progress in empirical and certified robustness promises to deliver reliable and deployable Deep Neural Networks (DNNs). Despite that success, most existing evaluations of DNN robustness have been done on images sampled from the same…
Despite the success on few-shot learning problems, most meta-learned models only focus on achieving good performance on clean examples and thus easily break down when given adversarially perturbed samples. While some recent works have shown…
Generalization in Reinforcement Learning (RL) aims to learn an agent during training that generalizes to the target environment. This paper studies RL generalization from a theoretical aspect: how much can we expect pre-training over…
Appearance changes due to weather and seasonal conditions represent a strong impediment to the robust implementation of machine learning systems in outdoor robotics. While supervised learning optimises a model for the training domain, it…
Despite the significant progress of deep reinforcement learning (RL) in solving sequential decision making problems, RL agents often overfit to training environments and struggle to adapt to new, unseen environments. This prevents robust…
We investigate the power of censoring techniques, first developed for learning {\em fair representations}, to address domain generalization. We examine {\em adversarial} censoring techniques for learning invariant representations from…
Domain randomization is a popular technique for improving domain transfer, often used in a zero-shot setting when the target domain is unknown or cannot easily be used for training. In this work, we empirically examine the effects of domain…
In reinforcement learning (RL), key components of many algorithms are the exploration strategy and replay buffer. These strategies regulate what environment data is collected and trained on and have been extensively studied in the RL…
Robotic tasks such as manipulation with visual inputs require image features that capture the physical properties of the scene, e.g., the position and configuration of objects. Recently, it has been suggested to learn such features in an…
Domain generalization (DG) aims to learn predictive models that can generalize to unseen domains. Most existing DG approaches focus on learning domain-invariant representations under the assumption of conditional distribution shift (i.e.,…
Unsupervised approaches for learning representations invariant to common transformations are used quite often for object recognition. Learning invariances makes models more robust and practical to use in real-world scenarios. Since data…
In this work, we address the challenge of zero-shot generalization (ZSG) in Reinforcement Learning (RL), where agents must adapt to entirely novel environments without additional training. We argue that understanding and utilizing…
The well known domain shift issue causes model performance to degrade when deployed to a new target domain with different statistics to training. Domain adaptation techniques alleviate this, but need some instances from the target domain to…
Continuous appearance shifts such as changes in weather and lighting conditions can impact the performance of deployed machine learning models. While unsupervised domain adaptation aims to address this challenge, current approaches do not…
Deep neural networks coupled with fast simulation and improved computation have led to recent successes in the field of reinforcement learning (RL). However, most current RL-based approaches fail to generalize since: (a) the gap between…
We present a domain adaptation based generative framework for zero-shot learning. Our framework addresses the problem of domain shift between the seen and unseen class distributions in zero-shot learning and minimizes the shift by…
Adversarial attacks on deep neural networks traditionally rely on a constrained optimization paradigm, where an optimization procedure is used to obtain a single adversarial perturbation for a given input example. In this work we frame the…
Generalization capability to unseen domains is crucial for machine learning models when deploying to real-world conditions. We investigate the challenging problem of domain generalization, i.e., training a model on multi-domain source data…
Recent studies have demonstrated that reinforcement learning (RL) agents are susceptible to adversarial manipulation, similar to vulnerabilities previously demonstrated in the supervised learning setting. While most existing work studies…