Portrait de Dzmitry Bahdanau

Dzmitry Bahdanau

Membre industriel principal
Chaire en IA Canada-CIFAR
Professeur adjoint, McGill University, École d'informatique
Chercheur scientifique IA, ServiceNow
Sujets de recherche
Apprentissage profond
Traitement du langage naturel
Google Scholar

Biographie

Dzmitry Bahdanau est professeur adjoint à l’Université McGill et chercheur à ServiceNow Element AI. Précédemment, il a obtenu son doctorat à l'Université de Montréal / Mila – Institut québécois d’intelligence artificielle en travaillant avec Yoshua Bengio. Il s'intéresse aux questions fondamentales et appliquées concernant la compréhension du langage naturel. Ses principaux domaines de recherche comprennent l'analyse sémantique, les interfaces utilisateur du langage, la généralisation systématique et les systèmes hybrides neuronaux symboliques.

Étudiants actuels

Jay Gala
Maîtrise recherche - McGill
Superviseur⋅e principal⋅e :
Siva Reddy
Site web
Google Scholar
Fengyuan Liu
Maîtrise recherche - McGill
Superviseur⋅e principal⋅e :
Siva Reddy
Site web
Github
Arkil Patel
Doctorat - McGill
Co-superviseur⋅e :
Siva Reddy
Site web
Github
Google Scholar

Publications

BabyAI 1.1
David Y. T. Hui
Maxime Chevalier-Boisvert
Dzmitry Bahdanau
Yoshua Bengio
BabyAI 1.1
David Y. T. Hui
Maxime Chevalier-Boisvert
Dzmitry Bahdanau
Yoshua Bengio
The BabyAI platform is designed to measure the sample efficiency of training an agent to follow grounded-language instructions. BabyAI 1.0 … (voir plus)presents baseline results of an agent trained by deep imitation or reinforcement learning. BabyAI 1.1 improves the agent’s architecture in three minor ways. This increases reinforcement learning sample efficiency by up to 3 × and improves imitation learning performance on the hardest level from 77% to 90 . 4% . We hope that these improvements increase the computational efficiency of BabyAI experiments and help users design better agents.
2021-01-01
(publié)
www.semanticscholar.org
BabyAI 1.1
David Y. T. Hui
Maxime Chevalier-Boisvert
Dzmitry Bahdanau
Yoshua Bengio
The BabyAI platform is designed to measure the sample efficiency of training an agent to follow grounded-language instructions. BabyAI 1.0 p… (voir plus)resents baseline results of an agent trained by deep imitation or reinforcement learning. BabyAI 1.1 improves the agent's architecture in three minor ways. This increases reinforcement learning sample efficiency by up to 3 times and improves imitation learning performance on the hardest level from 77 % to 90.4 %. We hope that these improvements increase the computational efficiency of BabyAI experiments and help users design better agents.
2020-07-24
ArXiv (prépublication)
arxiv.org
arxiv.org
BabyAI 1.1
David Y. T. Hui
Maxime Chevalier-Boisvert
Dzmitry Bahdanau
Yoshua Bengio
The BabyAI platform is designed to measure the sample efficiency of training an agent to follow grounded-language instructions. BabyAI 1.0 p… (voir plus)resents baseline results of an agent trained by deep imitation or reinforcement learning. BabyAI 1.1 improves the agent's architecture in three minor ways. This increases reinforcement learning sample efficiency by up to 3 times and improves imitation learning performance on the hardest level from 77 % to 90.4 %. We hope that these improvements increase the computational efficiency of BabyAI experiments and help users design better agents.
2020-07-24
ArXiv (prépublication)
arxiv.org
arxiv.org
BabyAI 1.1
David Y. T. Hui
Maxime Chevalier-Boisvert
Dzmitry Bahdanau
Yoshua Bengio
The BabyAI platform is designed to measure the sample efficiency of training an agent to follow grounded-language instructions. BabyAI 1.0 p… (voir plus)resents baseline results of an agent trained by deep imitation or reinforcement learning. BabyAI 1.1 improves the agent's architecture in three minor ways. This increases reinforcement learning sample efficiency by up to 3 times and improves imitation learning performance on the hardest level from 77 % to 90.4 %. We hope that these improvements increase the computational efficiency of BabyAI experiments and help users design better agents.
2020-07-24
ArXiv (prépublication)
arxiv.org
arxiv.org
BabyAI 1.1
David Y. T. Hui
Maxime Chevalier-Boisvert
Dzmitry Bahdanau
Yoshua Bengio
2020-07-24
ArXiv (prépublication)
arxiv.org
arxiv.org
Combating False Negatives in Adversarial Imitation Learning (Student Abstract)
Konrad Żołna
Chitwan Saharia
Léonard Boussioux
David Y. T. Hui
Maxime Chevalier-Boisvert
Dzmitry Bahdanau
Yoshua Bengio
2020-04-03
AAAI Conference on Artificial Intelligence (publié)
doi.org
CLOSURE: Assessing Systematic Generalization of CLEVR Models
Dzmitry Bahdanau
Harm de Vries
Timothy O'Donnell
Shikhar Murty
Philippe Beaudoin
Yoshua Bengio
Aaron Courville
2019-12-12
ArXiv (prépublication)
arxiv.org
arxiv.org
Automated curriculum generation for Policy Gradients from Demonstrations
Anirudh Srinivasan
Dzmitry Bahdanau
Maxime Chevalier-Boisvert
Yoshua Bengio
2019-12-01
ArXiv (prépublication)
arxiv.org
arxiv.org
BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning
Maxime Chevalier-Boisvert
Dzmitry Bahdanau
Salem Lahlou
Lucas Willems
Chitwan Saharia
Thien Huu Nguyen
Yoshua Bengio
Allowing humans to interactively train artificial agents to understand language instructions is desirable for both practical and scientific … (voir plus)reasons, but given the poor data efficiency of the current learning methods, this goal may require substantial research efforts. Here, we introduce the BabyAI research platform to support investigations towards including humans in the loop for grounded language learning. The BabyAI platform comprises an extensible suite of 19 levels of increasing difficulty. The levels gradually lead the agent towards acquiring a combinatorially rich synthetic language which is a proper subset of English. The platform also provides a heuristic expert agent for the purpose of simulating a human teacher. We report baseline results and estimate the amount of human involvement that would be required to train a neural network-based agent on some of the BabyAI levels. We put forward strong evidence that current deep learning methods are not yet sufficiently sample efficient when it comes to learning a language with compositional properties.
2019-01-01
ICLR.cc/2019/Conference (poster)
openreview.net
openreview.net
Systematic Generalization: What Is Required and Can It Be Learned?
Dzmitry Bahdanau*
Shikhar Murty*
Michael Noukhovitch
Thien Huu Nguyen
Harm de Vries
Aaron Courville
2019-01-01
ICLR.cc/2019/Conference (poster)
openreview.net
openreview.net
BabyAI: First Steps Towards Grounded Language Learning With a Human In the Loop
Maxime Chevalier-Boisvert
Dzmitry Bahdanau
Salem Lahlou
Lucas Willems
Chitwan Saharia
Thien Huu Nguyen
Yoshua Bengio
Allowing humans to interactively train artificial agents to understand language instructions is desirable for both practical and scientific … (voir plus)reasons, but given the poor data efficiency of the current learning methods, this goal may require substantial research efforts. Here, we introduce the BabyAI research platform to support investigations towards including humans in the loop for grounded language learning. The BabyAI platform comprises an extensible suite of 19 levels of increasing difficulty. The levels gradually lead the agent towards acquiring a combinatorially rich synthetic language which is a proper subset of English. The platform also provides a heuristic expert agent for the purpose of simulating a human teacher. We report baseline results and estimate the amount of human involvement that would be required to train a neural network-based agent on some of the BabyAI levels. We put forward strong evidence that current deep learning methods are not yet sufficiently sample efficient when it comes to learning a language with compositional properties.
2018-10-18
arXiv.org (prépublication)
dblp.uni-trier.de