相关论文: Learning World Models with Identifiable Factorizat…

Disentanglement is a difficult property to enforce in neural representations. This might be due, in part, to a formalization of the disentanglement problem that focuses too heavily on separating relevant factors of variation of the data in…

Generating explanations for reinforcement learning (RL) is challenging as actions may produce long-term effects on the future. In this paper, we develop a novel framework for explainable RL by learning a causal world model without prior…

Offline multi-agent reinforcement learning (MARL) aims to solve cooperative decision-making problems in multi-agent systems using pre-collected datasets. Existing offline MARL methods primarily constrain training within the dataset…

The utility of learning a dynamics/world model of the environment in reinforcement learning has been shown in a many ways. When using neural networks, however, these models suffer catastrophic forgetting when learned in a lifelong or…

World models enable agents to predict future dynamics conditioned on actions, making the choice of latent representation central to planning and control. Such representations are often either learned directly from pixels with limited…

As autonomous systems are increasingly deployed in open and uncertain settings, there is a growing need for trustworthy world models that can reliably predict future high-dimensional observations. The learned latent representations in world…

Deep latent variable models learn condensed representations of data that, hopefully, reflect the inner workings of the studied phenomena. Unfortunately, these latent representations are not statistically identifiable, meaning they cannot be…

Generalized latent factor analysis not only provides a useful latent embedding approach in statistics and machine learning, but also serves as a widely used tool across various scientific fields, such as psychometrics, econometrics, and…

We tackle the blackbox issue of deep neural networks in the settings of reinforcement learning (RL) where neural agents learn towards maximizing reward gains in an uncontrollable way. Such learning approach is risky when the interacting…

Humans learn quickly even in tasks that contain complex visual information. This is due in part to the efficient formation of compressed representations of visual information, allowing for better generalization and robustness. However,…

Inspired by how humans combine direct interaction with action-free experience (e.g., videos), we study world models that learn from heterogeneous data. Standard world models typically rely on action-conditioned trajectories, which limits…

Estimating graphical model structure from high-dimensional and undersampled data is a fundamental problem in many scientific fields. Existing approaches, such as GLASSO, latent variable GLASSO, and latent tree models, suffer from high…

We propose a learning-based framework for disentangling outdoor scenes into temporally-varying illumination and permanent scene factors. Inspired by the classic intrinsic image decomposition, our learning signal builds upon two insights: 1)…

Foundation Models (FMs) and World Models (WMs) offer complementary strengths in task generalization at different levels. In this work, we propose FOUNDER, a framework that integrates the generalizable knowledge embedded in FMs with the…

We propose a method for learning dynamical systems from high-dimensional empirical data that combines variational autoencoders and (spatio-)temporal attention within a framework designed to enforce certain scientifically-motivated…

A world model matters to an agent only through the state it constructs. That state must preserve some information, discard other information, and support some future function: prediction, control, planning, memory, grounding, or…

Learning physical dynamics in a series of non-stationary environments is a challenging but essential task for model-based reinforcement learning (MBRL) with visual inputs. It requires the agent to consistently adapt to novel tasks without…

While diffusion models excel at generating high-quality samples, their latent variables typically lack semantic meaning and are not suitable for representation learning. Here, we propose InfoDiffusion, an algorithm that augments diffusion…

One of the fundamental representation learning tasks is unsupervised sequential disentanglement, where latent codes of inputs are decomposed to a single static factor and a sequence of dynamic factors. To extract this latent information,…

Reinforcement Learning (RL) is essential for evolving Large Language Models (LLMs) into autonomous agents capable of long-horizon planning, yet a practical recipe for scaling RL in complex, multi-turn environments remains elusive. This…