In this work, we address the problem of learning optimal behavior from sub-optimal datasets in the context of goal-conditioned offline reinforcement learning. To do so, we propose a novel way of approximating the optimal value function for goal-conditioned offline RL problems under sparse rewards, symmetric and deterministic actions. We study a property for representations to recover optimality and propose a new optimization objective that leads to such property. We use the learned value function to guide the learning of a policy in an actor-critic fashion, a method we name MetricRL. Experimentally, we show how our method consistently outperforms other offline RL baselines in learning from sub-optimal offline datasets. Moreover, we show the effectiveness of our method in dealing with high-dimensional observations and in multi-goal tasks.
Recent advances in foundation models, especially in large multi-modal models and conversational agents, have ignited interest in the potential of generally capable embodied agents. Such agents would require the ability to perform new tasks in many different real-world environments. However, current foundation models fail to accurately model physical interactions with the real world thus not sufficient for Embodied AI. The study of causality lends itself to the construction of veridical world models, which are crucial for accurately predicting the outcomes of possible interactions. This paper focuses on the prospects of building foundation world models for the upcoming generation of embodied agents and presents a novel viewpoint on the significance of causality within these. We posit that integrating causal considerations is vital to facilitate meaningful physical interactions with the world. Finally, we demystify misconceptions about causality in this context and present our outlook for future research.
We introduce DexDiffuser, a novel dexterous grasping method that generates, evaluates, and refines grasps on partial object point clouds. DexDiffuser includes the conditional diffusion-based grasp sampler DexSampler and the dexterous grasp evaluator DexEvaluator. DexSampler generates high-quality grasps conditioned on object point clouds by iterative denoising of randomly sampled grasps. We also introduce two grasp refinement strategies: Evaluator-Guided Diffusion (EGD) and Evaluator-based Sampling Refinement (ESR). Our simulation and real-world experiments on the Allegro Hand consistently demonstrate that DexDiffuser outperforms the state-of-the-art multi-finger grasp generation method FFHNet with an, on average, 21.71--22.20\% higher grasp success rate.
In this work, we formally prove that, under certain conditions, if a neural network is invariant to a finite group then its weights recover the Fourier transform on that group. This provides a mathematical explanation for the emergence of Fourier features -- a ubiquitous phenomenon in both biological and artificial learning systems. The results hold even for non-commutative groups, in which case the Fourier transform encodes all the irreducible unitary group representations. Our findings have consequences for the problem of symmetry discovery. Specifically, we demonstrate that the algebraic structure of an unknown group can be recovered from the weights of a network that is at least approximately invariant within certain bounds. Overall, this work contributes to a foundation for an algebraic learning theory of invariant neural network representations.
Current training of motion style transfer systems relies on consistency losses across style domains to preserve contents, hindering its scalable application to a large number of domains and private data. Recent image transfer works show the potential of independent training on each domain by leveraging implicit bridging between diffusion models, with the content preservation, however, limited to simple data patterns. We address this by imposing biased sampling in backward diffusion while maintaining the domain independence in the training stage. We construct the bias from the source domain keyframes and apply them as the gradient of content constraints, yielding a framework with keyframe manifold constraint gradients (KMCGs). Our validation demonstrates the success of training separate models to transfer between as many as ten dance motion styles. Comprehensive experiments find a significant improvement in preserving motion contents in comparison to baseline and ablative diffusion-based style transfer models. In addition, we perform a human study for a subjective assessment of the quality of generated dance motions. The results validate the competitiveness of KMCGs.
We propose CAPGrasp, an $\mathbb{R}^3\times \text{SO(2)-equivariant}$ 6-DoF continuous approach-constrained generative grasp sampler. It includes a novel learning strategy for training CAPGrasp that eliminates the need to curate massive conditionally labeled datasets and a constrained grasp refinement technique that improves grasp poses while respecting the grasp approach directional constraints. The experimental results demonstrate that CAPGrasp is more than three times as sample efficient as unconstrained grasp samplers while achieving up to 38% grasp success rate improvement. CAPGrasp also achieves 4-10% higher grasp success rates than constrained but noncontinuous grasp samplers. Overall, CAPGrasp is a sample-efficient solution when grasps must originate from specific directions, such as grasping in confined spaces.
Lyrics often convey information about the songs that are beyond the auditory dimension, enriching the semantic meaning of movements and musical themes. Such insights are important in the dance choreography domain. However, most existing dance synthesis methods mainly focus on music-to-dance generation, without considering the semantic information. To complement it, we introduce JustLMD, a new multimodal dataset of 3D dance motion with music and lyrics. To the best of our knowledge, this is the first dataset with triplet information including dance motion, music, and lyrics. Additionally, we showcase a cross-modal diffusion-based network designed to generate 3D dance motion conditioned on music and lyrics. The proposed JustLMD dataset encompasses 4.6 hours of 3D dance motion in 1867 sequences, accompanied by musical tracks and their corresponding English lyrics.
We address the problem of learning representations from observations of a scene involving an agent and an external object the agent interacts with. To this end, we propose a representation learning framework extracting the location in physical space of both the agent and the object from unstructured observations of arbitrary nature. Our framework relies on the actions performed by the agent as the only source of supervision, while assuming that the object is displaced by the agent via unknown dynamics. We provide a theoretical foundation and formally prove that an ideal learner is guaranteed to infer an isometric representation, disentangling the agent from the object and correctly extracting their locations. We evaluate empirically our framework on a variety of scenarios, showing that it outperforms vision-based approaches such as a state-of-the-art keypoint extractor. We moreover demonstrate how the extracted representations enable the agent to solve downstream tasks via reinforcement learning in an efficient manner.
Endowing robots with tactile capabilities opens up new possibilities for their interaction with the environment, including the ability to handle fragile and/or soft objects. In this work, we equip the robot gripper with low-cost vision-based tactile sensors and propose a manipulation algorithm that adapts to both rigid and soft objects without requiring any knowledge of their properties. The algorithm relies on a touch and slip detection method, which considers the variation in the tactile images with respect to reference ones. We validate the approach on seven different objects, with different properties in terms of rigidity and fragility, to perform unplugging and lifting tasks. Furthermore, to enhance applicability, we combine the manipulation algorithm with a grasp sampler for the task of finding and picking a grape from a bunch without damaging~it.
Language-based fashion image editing allows users to try out variations of desired garments through provided text prompts. Inspired by research on manipulating latent representations in StyleCLIP and HairCLIP, we focus on these latent spaces for editing fashion items of full-body human datasets. Currently, there is a gap in handling fashion image editing due to the complexity of garment shapes and textures and the diversity of human poses. In this paper, we propose an editing optimizer scheme method called Text-Driven Garment Editing Mapper (TD-GEM), aiming to edit fashion items in a disentangled way. To this end, we initially obtain a latent representation of an image through generative adversarial network inversions such as Encoder for Editing (e4e) or Pivotal Tuning Inversion (PTI) for more accurate results. An optimization-based Contrasive Language-Image Pre-training (CLIP) is then utilized to guide the latent representation of a fashion image in the direction of a target attribute expressed in terms of a text prompt. Our TD-GEM manipulates the image accurately according to the target attribute, while other parts of the image are kept untouched. In the experiments, we evaluate TD-GEM on two different attributes (i.e., "color" and "sleeve length"), which effectively generates realistic images compared to the recent manipulation schemes.