A continuaciónSiguiente guía
Modelos de la Fundación NVIDIA Cosmos World
Empresas
GUÍA DE FUNDAMENTOS
A world model predicts environment dynamics from observations and actions.
Escuche esta guíaNarrado por IA · ~2 min
The cited World Models, DreamerV3, Genie, and GameNGen papers demonstrate different learned-simulation settings.
World models learn representations and dynamics that predict how an environment changes with actions. Ha and Schmidhuber’s 2018 work used a variational autoencoder to encode observations and a recurrent model for latent dynamics. Its CarRacing experiment used those learned features for control. In the separate DoomTakeCover experiment, the controller was trained inside the learned DoomRNN environment and then evaluated in the actual game; the authors did not train that controller directly in VizDoom. DreamerV3 reports collecting Minecraft diamonds from scratch without human demonstrations, using policy learning from imagined trajectories in its evaluated setup. Genie learns interactive environments from unlabeled internet video and can condition a generated environment on an image. GameNGen demonstrates a learned simulator for DOOM. These are different research settings, not evidence that one simulator can reliably reproduce every game or physical environment.
2018 World Models: the DoomTakeCover controller was trained in the learned DoomRNN dream environment and transferred to the actual game environment.
DreamerV3: the paper reports collecting Minecraft diamonds from scratch without human demonstrations under its evaluation setup.
Genie: the paper trains on unlabeled internet video and conditions generated interactive worlds on images.
GameNGen: the paper demonstrates a learned simulator for the named DOOM game.
A research direction is to measure long-horizon predictive accuracy and policy transfer for the intended task. Validate imagined experience against the real environment before relying on it for safety-critical decisions.
Boletín gratuito
Tres noticias verificadas sobre IA cada mañana de lunes a viernes, explicadas con claridad. Gratis para siempre y sin anuncios.
Un correo cada día laborable. Date de baja con un clic. Nunca vendemos ni compartimos tu dirección.
Ponte a prueba
Corrección inmediata en cada respuesta y un certificado para compartir, con un ID verificable, cuando apruebas un curso.
Apoya la educación gratuita sobre IA. AI Understanding es una organización sin fines de lucro 501(c)(3): sin anuncios ni muros de pago, nunca. Hacer una donación
A world model predicts environment dynamics from observations and actions. The cited World Models, DreamerV3, Genie, and GameNGen papers demonstrate different learned-simulation settings.
Un modelo mundial aprende la dinámica del entorno: a partir de un estado actual y una acción, predice la siguiente observación (y a menudo recompensa), lo que permite implementaciones imaginadas.
The authors trained the controller inside their learned DoomRNN environment and transferred it to the actual DoomTakeCover environment. This is distinct from their CarRacing feature-extraction experiment.
DreamerV3 reports reaching the diamond achievement in Minecraft from scratch without human demonstrations in its evaluated setup, using a learned world model for policy learning.
Genie es un entorno interactivo generativo que aprende de vídeos sin etiquetar para producir mundos 2D controlables por acción.
Las observaciones se codifican en un estado latente de baja dimensión y la función de transición predice el siguiente estado latente, lo que hace que los lanzamientos sean eficientes.
sigue aprendiendo
Más guías seleccionadas para este tema.
A continuaciónSiguiente guía
Modelos de la Fundación NVIDIA Cosmos World
Empresas