Up tókànItọsọna atẹle
NVIDIA Awọn awoṣe Cosmos World Foundation
Awọn ile-iṣẹ
Awọn ipilẹ Itọsọna
Awọn awoṣe Agbaye ati Awọn Simulators Kọ
A world model predicts environment dynamics from observations and actions.
Gbọ si itọsọna yiiAI-ṣe afihan · ~2 min
Lori iwe yi2 min ka
Akopọ
The cited World Models, DreamerV3, Genie, and GameNGen papers demonstrate different learned-simulation settings.
Jin Dive
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.
Real-World imuse
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.
Ọjọ iwaju ti Awọn awoṣe Agbaye ati Awọn Simulators Kọ ẹkọ
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.
Fifi o sinu iwa
Kini idi ti o ṣe pataki
- Awọn ipinnu diẹ sii. O ṣe iranlọwọ fun ọ lati ya sọtọ awọn iṣeduro imọ-ẹrọ lati ede tita.
- Iye owo ati isuna. O le beere awọn ibeere imuse to dara julọ ṣaaju lilo owo tabi akoko.
- Ẹgbẹ ati ṣiṣan iṣẹ. Awọn ẹgbẹ pẹlu oye pinpin ṣe ọja to dara julọ, eto imulo, ati awọn ipinnu ikẹkọ.
Ṣọra fun
- Awọn ẹgbẹ oriṣiriṣi le lo ọrọ kanna ni oriṣiriṣi, nitorinaa ṣalaye iwọn ni kutukutu.
- Awọn aṣepari le wo lagbara lakoko ti iṣẹ-aye gidi ko ṣe deede.
- Aibikita didara data ati awọn ero igbelewọn nigbagbogbo ṣẹda awọn abajade ẹlẹgẹ.
Next awọn igbesẹ
- Bẹrẹ pẹlu itumọ-ede itele ti abajade ti o nilo.
- Mu metiriki aṣeyọri kan ati ipo ikuna kan ṣaaju idanwo.
- Ṣiṣe awakọ kekere kan pẹlu data aṣoju, kii ṣe eto demo didan.
- Iwe-ipamọ nibiti Awọn awoṣe Agbaye ati Awọn Simulators ti Kọ ẹkọ ṣe iranlọwọ ati nibiti awọn ọna ti o rọrun dara julọ.
Tesiwaju Ṣiṣawari
Ìwé ìròyìn ọfẹ
Gba ìkànìyàn AI ojoojúmọ́
Ìtàn AI mẹta tó jẹ́rìí ní gbogbo owurọ́ ọjọ́ iṣẹ́, kọ́wé ní Gẹ̀ẹ́sì tó rọrùn. Ọfẹ́ fún gbogbo àkókò, kò sí ìpolówó.
Ìmeèlì kan ní gbogbo ọjọ́ iṣẹ́. Yọkúrò ní ìkànìyàn ní ìkànìyàn kan. A kò ta tàbí pín àdírẹ́sì rẹ.
Ṣe idanwo fun ara rẹ
Take the World Models and Learned Simulators quiz
Ìdáhùn lẹ́sẹ̀kẹsẹ̀ lórí gbogbo ìdáhùn, àti iwe-ẹ̀rí tó lè pin pẹ̀lú ID tó lè jẹ́rìí lẹ́yìn tí o bá kọ́ ẹ̀kọ́.
Ṣe àtìlẹ́yìn ẹ̀kọ́ AI ọfẹ́. AI Understanding jẹ́ àjọ àìní èrè 501(c)(3) — kò sí ìpolówó, kò sí àkúnya owó, ní gbogbo àkókò. Ṣe ẹbun kan
Awọn ibeere ti a beere nigbagbogbo
Kini Awọn awoṣe Agbaye ati Awọn Simulators Kọ?
A world model predicts environment dynamics from observations and actions. The cited World Models, DreamerV3, Genie, and GameNGen papers demonstrate different learned-simulation settings.
Kini iṣẹ pataki ti awoṣe agbaye kan?
Awoṣe agbaye kan kọ ẹkọ awọn agbara ayika: lati ipo lọwọlọwọ ati iṣe kan o sọ asọtẹlẹ akiyesi atẹle (ati ẹsan nigbagbogbo), ṣiṣe awọn iyipo ero inu.
In the 2018 World Models DoomTakeCover experiment, where was the controller trained?
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.
Iṣe akiyesi wo ni DeepMind's DreamerV3 ṣaṣeyọri?
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.
Kini Ẹmi Google ṣe?
Jini jẹ agbegbe ibaraenisepo ti ipilẹṣẹ ti o kọ ẹkọ lati fidio ti ko ni aami lati gbejade awọn agbaye 2D iṣakoso igbese.
Bawo ni ọpọlọpọ awọn awoṣe agbaye ṣe jẹ ki iṣoro asọtẹlẹ jẹ itusilẹ fun awọn igbewọle iwọn-giga bi awọn aworan?
Awọn akiyesi ti wa ni koodu sinu ipo wiwaba iwọn-kekere, ati iṣẹ iyipada n ṣe asọtẹlẹ ipo wiwaba atẹle, ṣiṣe awọn iyipo daradara.
Tesiwaju kikọ
Jẹmọ awọn itọsọna
Awọn itọsọna diẹ sii ti a yan fun koko yii