Related papers: NitroGen: An Open Foundation Model for Generalist …
Mean field theory provides an effective way of scaling multiagent reinforcement learning algorithms to environments with many agents that can be abstracted by a virtual mean agent. In this paper, we extend mean field multiagent algorithms…
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…
Developing general-purpose embodied agents is a core challenge in AI. Minecraft provides rich complexity and internet-scale data, but its slow speed and engineering overhead make it unsuitable for rapid prototyping. Crafter offers a…
We present a new public dataset with a focus on simulating robotic vision tasks in everyday indoor environments using real imagery. The dataset includes 20,000+ RGB-D images and 50,000+ 2D bounding boxes of object instances densely captured…
Human action recognition in computer vision has been widely studied in recent years. However, most algorithms consider only certain action specially with even high computational cost. That is not suitable for practical applications with…
Robot learning holds tremendous promise to unlock the full potential of flexible, general, and dexterous robot systems, as well as to address some of the deepest questions in artificial intelligence. However, bringing robot learning to the…
In this article, we present a new machine learning model by imitation based on the linguistic description of complex phenomena. The idea consists of, first, capturing the behaviour of human players by creating a computational perception…
Long-term video generation and prediction remain challenging tasks in computer vision, particularly in partially observable scenarios where cameras are mounted on moving platforms. The interaction between observed image frames and the…
The choice of action spaces is a critical yet unresolved challenge in developing capable, end-to-end trainable agents. This paper first presents a large-scale, systematic comparison of prominent abstracted action spaces and tokenizers for…
We propose a unified game-theoretical framework to perform classification and conditional image generation given limited supervision. It is formulated as a three-player minimax game consisting of a generator, a classifier and a…
Leveraging massive knowledge from large language models (LLMs), recent machine learning models show notable successes in general-purpose task solving in diverse domains such as computer vision and robotics. However, several significant…
The scarcity of large-scale robotic data has motivated the repurposing of foundation models from other modalities for policy learning. In this work, we introduce PhysGen (Learning Physics from Pretrained Video Generation Models), a scalable…
We evaluate an initial coding-agent system for ARC-AGI-3 in which the agent maintains an executable Python world model, verifies it against previous observations, refactors it toward simpler abstractions as a practical proxy for an MDL-like…
Long-horizon manipulation has been a long-standing challenge in the robotics community. We propose ReinforceGen, a system that combines task decomposition, data generation, imitation learning, and motion planning to form an initial…
The field of Game Theory provides a useful mechanism for modeling many decision-making scenarios. In participating in these scenarios individuals and groups adopt particular strategies, which generally perform with varying levels of…
Human-like agents are an increasingly important topic in games and beyond. Believable non-player characters enhance the gaming experience by improving immersion and providing entertainment. They also offer players the opportunity to engage…
We present Agent-to-Sim (ATS), a framework for learning interactive behavior models of 3D agents from casual longitudinal video collections. Different from prior works that rely on marker-based tracking and multiview cameras, ATS learns…
The acquisition of large-scale and diverse demonstration data are essential for improving robotic imitation learning generalization. However, generating such data for complex manipulations is challenging in real-world settings. We introduce…
Recently, text world games have been proposed to enable artificial agents to understand and reason about real-world scenarios. These text-based games are challenging for artificial agents, as it requires an understanding of and interaction…
This paper addresses the problem of both actively searching and tracking multiple unknown dynamic objects in a known environment with multiple cooperative autonomous agents with partial observability. The tracking of a target ends when the…