Related papers: AGWM: Affordance-Grounded World Models for Environ…

Planning with a learned model is arguably a key component of intelligence. There are several challenges in realizing such a component in large-scale reinforcement learning (RL) problems. One such challenge is dealing effectively with…

While reinforcement learning from scratch has shown impressive results in solving sequential decision-making tasks with efficient simulators, real-world applications with expensive interactions require more sample-efficient agents.…

We consider a dual model of decision making, in which an individual forms its opinion based on contrasting mechanisms of imitation and rational calculation. The decision making model (DMM) implements imitating behavior by means of a network…

World Action Models (WAMs) have emerged as a promising paradigm for robot control by modeling physical dynamics. Current WAMs generally follow two paradigms: the "Imagine-then-Execute" approach, which uses video prediction to infer actions…

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…

World models - learned internal simulators of environment dynamics - are rapidly becoming foundational to autonomous decision-making in robotics, autonomous vehicles, and agentic AI. By predicting future states in compressed latent spaces,…

Recent advances in video generation have spurred the development of world models capable of simulating 3D-consistent environments and interactions with static objects. However, a significant limitation remains in their ability to model…

We present exact algorithms for identifying deterministic-actions effects and preconditions in dynamic partially observable domains. They apply when one does not know the action model(the way actions affect the world) of a domain and must…

Affordance knowledge is a fundamental aspect of commonsense knowledge. Recent findings indicate that world knowledge emerges through large-scale self-supervised pretraining, motivating our exploration of acquiring affordance knowledge from…

In social sciences, researchers often face challenges when conducting large-scale experiments, particularly due to the simulations' complexity and the lack of technical expertise required to develop such frameworks. Agent-Based Modeling…

Large language models (LLMs) have achieved strong performance in language-centric tasks. However, in agentic settings, LLMs often struggle to anticipate action consequences and adapt to environment dynamics, highlighting the need for…

Infants learn actively in their environments, shaping their own learning curricula. They learn about their environments' affordances, that is, how local circumstances determine how their behavior can affect the environment. Here we model…

Traditional model-based reinforcement learning approaches learn a model of the environment dynamics without explicitly considering how it will be used by the agent. In the presence of misspecified model classes, this can lead to poor…

Language agents increasingly require persistent worlds in which they can act, remember, and learn. Existing approaches sit at two extremes: conventional web frameworks provide reliable but fixed contexts backed by databases, while fully…

We present SAGA, a versatile and adaptive framework for visuomotor control that can generalize across various environments, task objectives, and user specifications. To efficiently learn such capability, our key idea is to disentangle…

Artificial intelligence is essential to succeed in challenging activities that involve dynamic environments, such as object manipulation tasks in indoor scenes. Most of the state-of-the-art literature explores robotic grasping methods by…

Action-conditioned video prediction models (often referred to as world models) have shown strong potential for robotics applications, but existing approaches are often slow and struggle to capture physically consistent interactions over…

World models are self-supervised predictive models of how the world evolves. Humans learn world models by curiously exploring their environment, in the process acquiring compact abstractions of high bandwidth sensory inputs, the ability to…

World models enable agents to anticipate the effects of their actions by internalizing environment dynamics. In enterprise systems, however, these dynamics are often defined by tenant-specific business logic that varies across deployments…

We propose a developmental approach that allows a robot to interpret and describe the actions of human agents by reusing previous experience. The robot first learns the association between words and object affordances by manipulating the…