Title :

HoME: a Household Multimodal Environment

Author(s) :

Brodeur, Simon [Auteur]
Université de Sherbrooke [UdeS]
Perez, Ethan [Auteur]
Rice University [Houston]
Université de Montréal [UdeM]
Anand, Ankesh [Auteur]
Université de Montréal [UdeM]
Golemo, Florian [Auteur]
Flowing Epigenetic Robots and Systems [Flowers]
Université de Montréal [UdeM]
Celotti, Luca [Auteur]
Université de Sherbrooke [UdeS]
Strub, Florian [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Sequential Learning [SEQUEL]
Université de Montréal [UdeM]
Rouat, Jean [Auteur]
Université de Sherbrooke [UdeS]
Larochelle, Hugo [Auteur]
Google Brain
Courville, Aaron [Auteur]
Université de Montréal [UdeM]

Conference title :

NIPS 2017's Visually-Grounded Interaction and Language Workshop

City :

Long Beach

Country :

Etats-Unis d'Amérique

Start date of the conference :

2017-12-08

HAL domain(s) :

Informatique [cs]/Réseau de neurones [cs.NE]
Informatique [cs]/Intelligence artificielle [cs.AI]
Informatique [cs]/Vision par ordinateur et reconnaissance de formes [cs.CV]
Computer Science [cs]/Operations Research [math.OC]
Informatique [cs]/Son [cs.SD]

English abstract : [en]

We introduce HoME: a Household Multimodal Environment for artificial agents to learn from vision, audio, semantics, physics, and interaction with objects and other agents, all within a realistic context. HoME integrates ...
Show more >We introduce HoME: a Household Multimodal Environment for artificial agents to learn from vision, audio, semantics, physics, and interaction with objects and other agents, all within a realistic context. HoME integrates over 45,000 diverse 3D house layouts based on the SUNCG dataset, a scale which may facilitate learning, generalization, and transfer. HoME is an open-source, OpenAI Gym-compatible platform extensible to tasks in reinforcement learning, language grounding, sound-based navigation, robotics, multi-agent learning, and more. We hope HoME better enables artificial agents to learn as humans do: in an interactive, multimodal, and richly contextualized setting.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

Collections :

• Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL