Related papers: Disentangling Shape and Pose for Object-Centric De…

Active localization is the problem of generating robot actions that allow it to maximally disambiguate its pose within a reference map. Traditional approaches to this use an information-theoretic criterion for action selection and…

Disentangled representation learning has recently attracted a significant amount of attention, particularly in the field of image representation learning. However, learning the disentangled representations behind a graph remains largely…

State abstraction is an effective technique for planning in robotics environments with continuous states and actions, long task horizons, and sparse feedback. In object-oriented environments, predicates are a particularly useful form of…

Robots in uncertain real-world environments must perform both goal-directed and exploratory actions. However, most deep learning-based control methods neglect exploration and struggle under uncertainty. To address this, we adopt deep active…

An effective way to model the complex real world is to view the world as a composition of basic components of objects and transformations. Although humans through development understand the compositionality of the real world, it is…

Reinforcement Learning (RL) algorithms can learn robotic control tasks from visual observations, but they often require a large amount of data, especially when the visual scene is complex and unstructured. In this paper, we explore how the…

Active soft bodies can affect their shape through an internal actuation mechanism that induces a deformation. Similar to recent work, this paper utilizes a differentiable, quasi-static, and physics-based simulation layer to optimize for…

Recent work has shown how predictive modeling can endow agents with rich knowledge of their surroundings, improving their ability to act in complex environments. We propose question-answering as a general paradigm to decode and understand…

While reinforcement learning has achieved considerable successes in recent years, state-of-the-art models are often still limited by the size of state and action spaces. Model-free reinforcement learning approaches use some form of state…

An intelligent agent operating in the real-world must balance achieving its goal with maintaining the safety and comfort of not only itself, but also other participants within the surrounding scene. This requires jointly reasoning about the…

Modeling group actions on latent representations enables controllable transformations of high-dimensional image data. Prior works applying group-theoretic priors or modeling transformations typically operate in the high-dimensional data…

Active inference is a first principle account of how autonomous agents operate in dynamic, non-stationary environments. This problem is also considered in reinforcement learning (RL), but limited work exists on comparing the two approaches…

Questions convey information about the questioner, namely what one does not know. In this paper, we propose a novel approach to allow a learning agent to ask what it considers as tricky to predict, in the course of producing a final output.…

Disentanglement is a useful property in representation learning which increases the interpretability of generative models such as Variational autoencoders (VAE), Generative Adversarial Models, and their many variants. Typically in such…

We study the task of embodied visual active learning, where an agent is set to explore a 3d environment with the goal to acquire visual scene understanding by actively selecting views for which to request annotation. While accurate on some…

Agent-Based Models are very useful for simulation of physical or social processes, such as the spreading of a pandemic in a city. Such models proceed by specifying the behavior of individuals (agents) and their interactions, and…

Graph representation of objects and their relations in a scene, known as a scene graph, provides a precise and discernible interface to manipulate a scene by modifying the nodes or the edges in the graph. Although existing works have shown…

Active Inference is a closed-loop computational theoretical basis for understanding behaviour, based on agents with internal probabilistic generative models that encode their beliefs about how hidden states in their environment cause their…

Active inference is a formal approach to study cognition based on the notion that adaptive agents can be seen as engaging in a process of approximate Bayesian inference, via the minimisation of variational and expected free energies.…

Rich phenomena from complex systems have long intrigued researchers, and yet modeling system micro-dynamics and inferring the forms of interaction remain challenging for conventional data-driven approaches, being generally established by…