Il prossimoProssima guida
Modelli della Fondazione NVIDIA Cosmos World
Aziende
GUIDA AI FONDAMENTALI
A world model predicts environment dynamics from observations and actions.
Ascolta questa guidaNarrato dall'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.
Newsletter gratuita
Tre storie verificate sull'IA ogni mattina nei giorni feriali, scritte in un inglese semplice. Gratuito per sempre, senza pubblicità.
Un'email ogni giorno feriale. Disiscriviti con un clic. Non vendiamo né condividiamo mai il tuo indirizzo.
Mettiti alla prova
Feedback immediato su ogni risposta e un certificato condivisibile con un ID verificabile una volta superato un corso.
Sostieni l'istruzione gratuita sull'IA. AI Understanding è un'organizzazione non profit 501(c)(3) — nessun annuncio, nessun paywall, mai. Fai una donazione
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 modello mondiale apprende le dinamiche ambientali: da uno stato attuale e da un’azione prevede l’osservazione successiva (e spesso la ricompensa), consentendo implementazioni immaginarie.
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 è un ambiente interattivo generativo che impara da video senza etichetta per produrre mondi 2D controllabili dall'azione.
Le osservazioni sono codificate in uno stato latente a bassa dimensionalità e la funzione di transizione prevede il successivo stato latente, rendendo efficienti i rollout.
Continua a imparare
Altre guide selezionate per questo argomento
Il prossimoProssima guida
Modelli della Fondazione NVIDIA Cosmos World
Aziende