Related papers: Goal-Directed Planning for Habituated Agents by Ac…

Bounded rational agents often make decisions by evaluating a finite selection of choices, typically derived from a reference point termed the $`$default policy,' based on previous experience. However, the inherent rigidity of the static…

Much of model-based reinforcement learning involves learning a model of an agent's world, and training an agent to leverage this model to perform a task more efficiently. While these models are demonstrably useful for agents, every…

We present a neuro-inspired framework for embodied planning and control. Building on three principles that enable fast and highly effective goal-directed behavior in the mammalian brain - paired forward/inverse internal models, open-loop…

We present an approach to learn an object-centric forward model, and show that this allows us to plan for sequences of actions to achieve distant desired goals. We propose to model a scene as a collection of objects, each with an explicit…

Modern learning systems increasingly rely on amortized learning - the idea of reusing computation or inductive biases shared across tasks to enable rapid generalization to novel problems. This principle spans a range of approaches,…

Imitation learning offers a promising path for robots to learn general-purpose behaviors, but traditionally has exhibited limited scalability due to high data supervision requirements and brittle generalization. Inspired by recent advances…

A generalist robot equipped with learned skills must be able to perform many tasks in many different environments. However, zero-shot generalization to new settings is not always possible. When the robot encounters a new environment or…

Generative Adversarial Networks (GANs) have been shown to be powerful and flexible priors when solving inverse problems. One challenge of using them is overcoming representation error, the fundamental limitation of the network in…

Many problems in machine learning are naturally expressed in the language of undirected graphical models. Here, we propose black-box learning and inference algorithms for undirected models that optimize a variational approximation to the…

Modeling generalized robot control policies poses ongoing challenges for language-guided robot manipulation tasks. Existing methods often struggle to efficiently utilize cross-dataset resources or rely on resource-intensive vision-language…

Deep generative frameworks including GANs and normalizing flow models have proven successful at filling in missing values in partially observed data samples by effectively learning -- either explicitly or implicitly -- complex,…

Traditional robotic approaches rely on an accurate model of the environment, a detailed description of how to perform the task, and a robust perception system to keep track of the current state. On the other hand, reinforcement learning…

Active inference is a unifying theory for perception and action resting upon the idea that the brain maintains an internal model of the world by minimizing free energy. From a behavioral perspective, active inference agents can be seen as…

Infants are experts at playing, with an amazing ability to generate novel structured behaviors in unstructured environments that lack clear extrinsic reward signals. We seek to mathematically formalize these abilities using a neural network…

General-purpose robotic manipulation, including reach and grasp, is essential for deployment into households and workspaces involving diverse and evolving tasks. Recent advances propose using large pre-trained models, such as Large Language…

Active inference is a mathematical framework for understanding how agents (biological or artificial) interact with their environments, enabling continual adaptation and decision-making. It combines Bayesian inference and free energy…

Imitation learning is a widely used approach for training agents to replicate expert behavior in complex decision-making tasks. However, existing methods often struggle with compounding errors and limited generalization, due to the inherent…

We present Generative Predictive Control (GPC), an inference-time method for improving pretrained behavior-cloning policies without retraining. GPC augments a frozen diffusion policy at deployment with an action-conditioned world model…

The aim of this paper is to study the reward based policy exploration problem in a supervised learning approach and enable robots to form complex movement trajectories in challenging reward settings and search spaces. For this, the…

Although humans live in an open-ended world and endlessly face new challenges, they do not have to learn from scratch each time they face the next one. Rather, they have access to a handful of previously learned skills, which they rapidly…