SelanjutnyaPanduan berikutnya
Model Yayasan Dunia NVIDIA Cosmos
Perusahaan
PANDUAN Dasar
A world model predicts environment dynamics from observations and actions.
Dengarkan panduan iniDiceritakan oleh AI · ~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.
Buletin gratis
Tiga cerita AI terverifikasi setiap pagi hari kerja, ditulis dalam bahasa Inggris sederhana. Gratis selamanya, tanpa iklan.
Satu email setiap hari kerja. Berhenti berlangganan dalam satu klik. Kami tidak pernah menjual atau membagikan alamat Anda.
Uji diri Anda sendiri
Umpan balik instan untuk setiap jawaban, dan sertifikat yang dapat dibagikan dengan ID yang dapat diverifikasi setelah Anda lulus kursus.
Mendukung pendidikan AI gratis. AI Understanding adalah organisasi nirlaba 501(c)(3) — tanpa iklan, tanpa paywall, selamanya. Berikan sumbangan
A world model predicts environment dynamics from observations and actions. The cited World Models, DreamerV3, Genie, and GameNGen papers demonstrate different learned-simulation settings.
Model dunia mempelajari dinamika lingkungan: dari keadaan saat ini dan tindakan yang diprediksi oleh model tersebut pada pengamatan berikutnya (dan sering kali memberikan imbalan), sehingga memungkinkan peluncuran yang dibayangkan.
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 adalah lingkungan interaktif generatif yang belajar dari video tanpa label untuk menghasilkan dunia 2D yang dapat dikontrol tindakan.
Pengamatan dikodekan ke dalam keadaan laten berdimensi rendah, dan fungsi transisi memprediksi keadaan laten berikutnya, sehingga membuat peluncuran menjadi efisien.
Teruslah belajar
Panduan lainnya dipilih untuk topik ini
SelanjutnyaPanduan berikutnya
Model Yayasan Dunia NVIDIA Cosmos
Perusahaan