Related papers: Sparse Masked Attention Policies for Reliable Gene…
Reinforcement Learning faces an important challenge in partial observable environments that has long-term dependencies. In order to learn in an ambiguous environment, an agent has to keep previous perceptions in a memory. Earlier memory…
The pandemic of these very recent years has led to a dramatic increase in people wearing protective masks in public venues. This poses obvious challenges to the pervasive use of face recognition technology that now is suffering a decline in…
Generalized planning is concerned with the computation of general policies that solve multiple instances of a planning domain all at once. It has been recently shown that these policies can be computed in two steps: first, a suitable…
Abstraction reasoning is a long-standing challenge in artificial intelligence. Recent studies suggest that many of the deep architectures that have triumphed over other domains failed to work well in abstract reasoning. In this paper, we…
Partial observability of the underlying states generally presents significant challenges for reinforcement learning (RL). In practice, certain \emph{privileged information}, e.g., the access to states from simulators, has been exploited in…
Diffusion models have shown remarkable success across a wide range of generative tasks. However, they often suffer from spatially inconsistent generation, arguably due to the inherent locality of their denoising mechanisms. This can yield…
We derive a new theoretical interpretation of the reweighted losses that are widely used for training diffusion models. Our method is based on constructing a cascade of time-dependent variational lower bounds on the data log-likelihood,…
Modelling the behaviours of other agents is essential for understanding how agents interact and making effective decisions. Existing methods for agent modelling commonly assume knowledge of the local observations and chosen actions of the…
Most efforts in interpretability in deep learning have focused on (1) extracting explanations of a specific downstream task in relation to the input features and (2) imposing constraints on the model, often at the expense of predictive…
The task of detecting whether a person wears a face mask from speech is useful in modelling speech in forensic investigations, communication between surgeons or people protecting themselves against infectious diseases such as COVID-19. In…
Off-policy evaluation in reinforcement learning offers the chance of using observational data to improve future outcomes in domains such as healthcare and education, but safe deployment in high stakes settings requires ways of assessing its…
A reinforcement learning agent that needs to pursue different goals across episodes requires a goal-conditional policy. In addition to their potential to generalize desirable behavior to unseen goals, such policies may also enable…
Transferable adversarial attack is always in the spotlight since deep learning models have been demonstrated to be vulnerable to adversarial samples. However, existing physical attack methods do not pay enough attention on transferability…
Deep reinforcement learning (deep RL) excels in various domains but lacks generalizability and interpretability. On the other hand, programmatic RL methods (Trivedi et al., 2021; Liu et al., 2023) reformulate RL tasks as synthesizing…
Recently the emergence of novel presentation attacks has drawn increasing attention to face anti-spoofing. However, existing methods tend to memorize data patterns from the training set, resulting in poor generalization to unknown attack…
In this paper, we explore deep reinforcement learning algorithms for vision-based robotic grasping. Model-free deep reinforcement learning (RL) has been successfully applied to a range of challenging environments, but the proliferation of…
Active learning enables efficient model training by leveraging interactions between machine learning agents and human annotators. We study and propose a novel framework that formulates batch active learning from the sparse approximation's…
Nowadays, machine learning models, especially neural networks, become prevalent in many real-world applications.These models are trained based on a one-way trip from user data: as long as users contribute their data, there is no way to…
We propose a simple, statistically principled, and theoretically justified method to improve supervised learning when the training set is not representative, a situation known as covariate shift. We build upon a well-established methodology…
Training a robust system, e.g.,Speech to Text (STT), requires large datasets. Variability present in the dataset such as unwanted nuisances and biases are the reason for the need of large datasets to learn general representations. In this…