Related papers: Structured World Belief for Reinforcement Learning…

Object manipulation capabilities are essential skills that set apart embodied agents engaging with the world, especially in the realm of robotics. The ability to predict outcomes of interactions with objects is paramount in this setting.…

In a sequential decision-making problem, the information structure is the description of how events in the system occurring at different points in time affect each other. Classical models of reinforcement learning (e.g., MDPs, POMDPs)…

The interpretation of spatial references is highly contextual, requiring joint inference over both language and the environment. We consider the task of spatial reasoning in a simulated environment, where an agent can act and receive…

Model-based methods have recently shown promising for offline reinforcement learning (RL), aiming to learn good policies from historical data without interacting with the environment. Previous model-based offline RL methods learn fully…

As the intermediate-level representations bridging the two levels, structured representations of visual scenes, such as visual relationships between pairwise objects, have been shown to not only benefit compositional models in learning to…

We consider the problem of imitation learning from expert demonstrations in partially observable Markov decision processes (POMDPs). Belief representations, which characterize the distribution over the latent states in a POMDP, have been…

In this study I proposed a filtering beliefs method for improving performance of Partially Observable Markov Decision Processes(POMDPs), which is a method wildly used in autonomous robot and many other domains concerning control policy. My…

The ability to simulate the effects of future actions on the world is a crucial ability of intelligent embodied agents, enabling agents to anticipate the effects of their actions and make plans accordingly. While a large body of existing…

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…

Although foundation models (FMs) claim to be powerful, their generalization ability significantly decreases when faced with distribution shifts, weak supervision, or malicious attacks in the open world. On the other hand, most domain…

Object-based factorizations provide a useful level of abstraction for interacting with the world. Building explicit object representations, however, often requires supervisory signals that are difficult to obtain in practice. We present a…

Self-supervision allows learning meaningful representations of natural images, which usually contain one central object. How well does it transfer to multi-entity scenes? We discuss key aspects of learning structured object-centric…

Current deep reinforcement learning (RL) approaches incorporate minimal prior knowledge about the environment, limiting computational and sample efficiency. \textit{Objects} provide a succinct and causal description of the world, and many…

World simulation has gained increasing popularity due to its ability to model virtual environments and predict the consequences of actions. However, the limited temporal context window often leads to failures in maintaining long-term…

Although pretrained language models (PTLMs) contain significant amounts of world knowledge, they can still produce inconsistent answers to questions when probed, even after specialized training. As a result, it can be hard to identify what…

Object-centric representation learning aims to decompose visual scenes into fixed-size vectors called "slots" or "object files", where each slot captures a distinct object. Current state-of-the-art object-centric models have shown…

World models require robust relational understanding to support prediction, reasoning, and control. While object-centric representations provide a useful abstraction, they are not sufficient to capture interaction-dependent dynamics. We…

In most real-world reinforcement learning applications, state information is only partially observable, which breaks the Markov decision process assumption and leads to inferior performance for algorithms that conflate observations with…

Online decision making under uncertainty in partially observable domains, also known as Belief Space Planning, is a fundamental problem in robotics and Artificial Intelligence. Due to an abundance of plausible future unravelings,…

A crucial ability of human intelligence is to build up models of individual 3D objects from partial scene observations. Recent works achieve object-centric generation but without the ability to infer the representation, or achieve 3D scene…