相关论文: Active World Model Learning with Progress Curiosit…

We provide a dataset that enables the creation of learning agents that can build knowledge graph-based world models of interactive narratives. Interactive narratives -- or text-adventure games -- are partially observable environments…

Driven by curiosity, humans have continually sought to explore and understand the world around them, leading to the invention of various tools to satiate this inquisitiveness. Despite not having the capacity to process and memorize vast…

Children learn continually by asking questions about the concepts they are most curious about. With robots becoming an integral part of our society, they must also learn unknown concepts continually by asking humans questions. The paper…

This paper presents the World-Action Model (WAM), an action-regularized world model that jointly reasons over future visual observations and the actions that drive state transitions. Unlike conventional world models trained solely via image…

Real-world driving requires people to observe the current environment, anticipate the future, and make appropriate driving decisions. This requirement is aligned well with the capabilities of world models, which understand the environment…

General-purpose world models promise scalable policy evaluation, optimization, and planning, yet achieving the required level of robustness remains challenging. Unlike policy learning, which primarily focuses on optimal actions, a world…

Model-based Reinforcement Learning approaches have the promise of being sample efficient. Much of the progress in learning dynamics models in RL has been made by learning models via supervised learning. But traditional model-based…

Autonomous robots need to be able to adapt to unforeseen situations and to acquire new skills through trial and error. Reinforcement learning in principle offers a suitable methodological framework for this kind of autonomous learning.…

The autonomous learning of new goals in robotics remains a complex issue to address. Here, we propose a model where curiosity influence learning flexibility. To do so, this paper proposes to root curiosity and attention together by taking…

When building a world model, a common assumption is that the environment has a single, unchanging underlying causal rule, like applying Newton's laws to every situation. In reality, what appears as a drifting causal mechanism is often the…

The paradigm of learning-based robotics holds immense promise, yet its translation to real-world applications is critically hindered by the sample inefficiency and brittleness of conventional model-free reinforcement learning algorithms. In…

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…

Model-based curiosity combines active learning approaches to optimal sampling with the information gain based incentives for exploration presented in the curiosity literature. Existing model-based curiosity methods look to approximate…

In recent years, Model-based Multi-Agent Reinforcement Learning (MARL) has demonstrated significant advantages over model-free methods in terms of sample efficiency by using independent environment dynamics world models for data sample…

Despite the potential of language model-based agents to solve real-world tasks such as web navigation, current methods still struggle with long-horizon tasks with complex action trajectories. In contrast, humans can flexibly solve complex…

What if a video generation model could not only imagine a plausible future, but the correct one, accurately reflecting how the world changes with each action? We address this question by presenting the Egocentric World Model (EgoWM), a…

Exploring the spectrum of novel behaviors a physical system can produce can be a labor-intensive task. Active learning is a collection of iterative sampling techniques developed in response to this challenge. However, these techniques often…

We propose the use of latent space generative world models to address the covariate shift problem in autonomous driving. A world model is a neural network capable of predicting an agent's next state given past states and actions. By…

Measuring learning progress is essential for curiosity-driven exploration in reinforcement learning, but widely used signals such as prediction error often fail to distinguish meaningful, learnable patterns from random noise. This paper…

Leveraging future observation modeling to facilitate action generation presents a promising avenue for enhancing the capabilities of Vision-Language-Action (VLA) models. However, existing approaches struggle to strike a balance between…