Related papers: AgentWorld: An Interactive Simulation Platform for…
Imaginative play is an area of creativity that could allow robots to engage with the world around them in a much more personified way. Imaginary play can be seen as taking real objects and locations and using them as imaginary objects and…
We introduce a new software toolbox for agent-based simulation. Facilitating rapid prototyping by offering a user-friendly Python API, its core rests on an efficient C++ implementation to support simulation of large-scale multi-agent…
This paper presents BattleAgent, an emulation system that combines the Large Vision-Language Model and Multi-agent System. This novel system aims to simulate complex dynamic interactions among multiple agents, as well as between agents and…
Interactive multi-agent simulation algorithms are used to compute the trajectories and behaviors of different entities in virtual reality scenarios. However, current methods involve considerable parameter tweaking to generate plausible…
Replicating existing agent-based models poses significant challenges, particularly for those new to the field. This article presents an all-encompassing guide to re-implementing agent-based models, encompassing vital concepts such as…
How can we imbue robots with the ability to manipulate objects precisely but also to reason about them in terms of abstract concepts? Recent works in manipulation have shown that end-to-end networks can learn dexterous skills that require…
We explore building generative neural network models of popular reinforcement learning environments. Our world model can be trained quickly in an unsupervised manner to learn a compressed spatial and temporal representation of the…
Deploying robots in open-ended unstructured environments such as homes has been a long-standing research problem. However, robots are often studied only in closed-off lab settings, and prior mobile manipulation work is restricted to…
Recent advancements in large foundation models have remarkably enhanced our understanding of sensory information in open-world environments. In leveraging the power of foundation models, it is crucial for AI research to pivot away from…
With the rapid advancement of large language models (LLMs), recent years have witnessed many promising studies on leveraging LLM-based agents to simulate human social behavior. While prior work has demonstrated significant potential across…
Human-like Agents with diverse and dynamic personalities could serve as an essential design probe in the process of user-centered design, thereby enabling designers to enhance the user experience of interactive applications. In this…
Training agents to act in embodied environments typically requires vast training data or access to accurate simulation, neither of which exists for many cases in the real world. Instead, world models are emerging as an alternative…
Automated scientific discovery promises to accelerate progress across scientific domains. However, developing and evaluating an AI agent's capacity for end-to-end scientific reasoning is challenging as running real-world experiments is…
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…
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…
Effective robotic manipulation requires policies that can anticipate physical outcomes and adapt to real-world environments. Effective robotic manipulation requires policies that can anticipate physical outcomes and adapt to real-world…
Believable proxies of human behavior can empower interactive applications ranging from immersive environments to rehearsal spaces for interpersonal communication to prototyping tools. In this paper, we introduce generative…
Agent-Based Modeling and Simulation (ABMS) is a simple and yet powerful method for simulation of interactions among individual agents. Using ABMS, different phenomena can be modeled and simulated without spending additional time on…
This paper presents ShareVerse, a video generation framework enabling multi-agent shared world modeling, addressing the gap in existing works that lack support for unified shared world construction with multi-agent interaction. ShareVerse…
We present RoboGen, a generative robotic agent that automatically learns diverse robotic skills at scale via generative simulation. RoboGen leverages the latest advancements in foundation and generative models. Instead of directly using or…