Related papers: Measuring Visual Generalization in Continuous Cont…
In the field of computer vision, data augmentation is widely used to enrich the feature complexity of training datasets with deep learning techniques. However, regarding the generalization capabilities of models, the difference in…
Imitation learning is an effective approach for training game-playing agents and, consequently, for efficient game production. However, generalization - the ability to perform well in related but unseen scenarios - is an essential…
Q-learning algorithms are appealing for real-world applications due to their data-efficiency, but they are very prone to overfitting and training instabilities when trained from visual observations. Prior work, namely SVEA, finds that…
Reasoning from diverse observations is a fundamental capability for generalist robot policies to operate in a wide range of environments. Despite recent advancements, many large-scale robotic policies still remain sensitive to key sources…
Self-supervised learning aims to learn representations from the data itself without explicit manual supervision. Existing efforts ignore a crucial aspect of self-supervised learning - the ability to scale to large amount of data because…
The generalization ability of visuomotor policy is crucial, as a good policy should be deployable across diverse scenarios. Some methods can collect large amounts of trajectory augmentation data to train more generalizable imitation…
Deep reinforcement learning (RL) agents often fail to generalize to unseen scenarios, even when they are trained on many instances of semantically similar environments. Data augmentation has recently been shown to improve the sample…
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,…
We witnessed a massive growth in the supervised learning paradigm in the past decade. Supervised learning requires a large amount of labeled data to reach state-of-the-art performance. However, labeling the samples requires a lot of human…
The generalization gap in reinforcement learning (RL) has been a significant obstacle that prevents the RL agent from learning general skills and adapting to varying environments. Increasing the generalization capacity of the RL systems can…
For an autonomous agent to fulfill a wide range of user-specified goals at test time, it must be able to learn broadly applicable and general-purpose skill repertoires. Furthermore, to provide the requisite level of generality, these skills…
Due to the realization that deep reinforcement learning algorithms trained on high-dimensional tasks can strongly overfit to their training environments, there have been several studies that investigated the generalization performance of…
Visual reinforcement learning (RL), which makes decisions directly from high-dimensional visual inputs, has demonstrated significant potential in various domains. However, deploying visual RL techniques in the real world remains challenging…
Recent advances in deep reinforcement learning and scalable photorealistic simulation have led to increasingly mature embodied AI for various visual tasks, including navigation. However, while impressive progress has been made for teaching…
While agents trained by Reinforcement Learning (RL) can solve increasingly challenging tasks directly from visual observations, generalizing learned skills to novel environments remains very challenging. Extensive use of data augmentation…
Text-based games (TBGs) have become a popular proving ground for the demonstration of learning-based agents that make decisions in quasi real-world settings. The crux of the problem for a reinforcement learning agent in such TBGs is…
Improving generalization is one key challenge in embodied AI, where obtaining large-scale datasets across diverse scenarios is costly. Traditional weak augmentations, such as cropping and flipping, are insufficient for improving a model's…
The data-driven approach to robot control has been gathering pace rapidly, yet generalization to unseen task domains remains a critical challenge. We argue that the key to generalization is representations that are (i) rich enough to…
Deep learning has achieved remarkable results in many computer vision tasks. Deep neural networks typically rely on large amounts of training data to avoid overfitting. However, labeled data for real-world applications may be limited. By…
Data augmentation has proved extremely useful by increasing training data variance to alleviate overfitting and improve deep neural networks' generalization performance. In medical image analysis, a well-designed augmentation policy usually…