Related papers: Efficient Embedding of Semantic Similarity in Cont…
Differentiable simulators promise to improve sample efficiency in robot learning by providing analytic gradients of the system dynamics. Yet, their application to contact-rich tasks like locomotion is complicated by the inherently…
In the era of Big Data, scalable and accurate clustering algorithms for high-dimensional data are essential. We present new Bayesian Distance Clustering (BDC) models and inference algorithms with improved scalability while maintaining the…
Behavior cloning of expert demonstrations can speed up learning optimal policies in a more sample-efficient way over reinforcement learning. However, the policy cannot extrapolate well to unseen states outside of the demonstration data,…
We propose a novel framework for multi-task reinforcement learning (MTRL). Using a variational inference formulation, we learn policies that generalize across both changing dynamics and goals. The resulting policies are parametrized by…
We focus on the problem of teaching a robot to solve tasks presented sequentially, i.e., in a continual learning scenario. The robot should be able to solve all tasks it has encountered, without forgetting past tasks. We provide preliminary…
In this paper, we discuss a framework for teaching bimanual manipulation tasks by imitation. To this end, we present a system and algorithms for learning compliant and contact-rich robot behavior from human demonstrations. The presented…
Deep Metric Learning (DML) proposes to learn metric spaces which encode semantic similarities as embedding space distances. These spaces should be transferable to classes beyond those seen during training. Commonly, DML methods task…
Large Language Models (LLMs) have shown impressive potential to simulate human behavior. We identify a fundamental challenge in using them to simulate experiments: when LLM-simulated subjects are blind to the experimental design (as is…
Reinforcement learning has received high research interest for developing planning approaches in automated driving. Most prior works consider the end-to-end planning task that yields direct control commands and rarely deploy their algorithm…
Many popular policy gradient methods for reinforcement learning follow a biased approximation of the policy gradient known as the discounted approximation. While it has been shown that the discounted approximation of the policy gradient is…
We study various distance-like entanglement measures of multipartite states under certain symmetries. Using group averaging techniques we provide conditions under which the relative entropy of entanglement, the geometric measure of…
Learning the embedding space, where semantically similar objects are located close together and dissimilar objects far apart, is a cornerstone of many computer vision applications. Existing approaches usually learn a single metric in the…
Reinforcement learning offers the promise of automating the acquisition of complex behavioral skills. However, compared to commonly used and well-understood supervised learning methods, reinforcement learning algorithms can be brittle,…
Disentanglement is a highly desirable property of representation due to its similarity with human's understanding and reasoning. This improves interpretability, enables the performance of down-stream tasks, and enables controllable…
We propose a model-free deep reinforcement learning method that leverages a small amount of demonstration data to assist a reinforcement learning agent. We apply this approach to robotic manipulation tasks and train end-to-end visuomotor…
Vision-language models can encode societal biases and stereotypes, but there are challenges to measuring and mitigating these multimodal harms due to lacking measurement robustness and feature degradation. To address these challenges, we…
An asymptotic entanglement measure for any bipartite states is derived in the light of the dense coding capacity optimized with respect to local quantum operations and classical communications. General properties and some examples with…
At the core of self-supervised learning for vision is the idea of learning invariant or equivariant representations with respect to a set of data transformations. This approach, however, introduces strong inductive biases, which can render…
Recent efforts on training visual navigation agents conditioned on language using deep reinforcement learning have been successful in learning policies for different multimodal tasks, such as semantic goal navigation and embodied question…
We propose a semantic similarity metric for image registration. Existing metrics like euclidean distance or normalized cross-correlation focus on aligning intensity values, giving difficulties with low intensity contrast or noise. Our…