Laboratoire de recherche Microsoft - Montréal
Télécharger
Implementation of SPIBB-DQN
mai 2019
This project can be used to reproduce the DQN implementation presented in the ICML2019 paper: Safe Policy Improvement with Baseline Bootstrapping, by Romain Laroche, Paul Trichelair, and Rémi Tachet des Combes. For the finite MDPs experiments, please refer to git…
Implementation of Safe Policy Improvement with Baseline Bootstrapping
mai 2019
This project can be used to reproduce the finite MDPs experiments presented in the ICML2019 paper: Safe Policy Improvement with Baseline Bootstrapping, by Romain Laroche, Paul Trichelair, and Rémi Tachet des Combes. For the DQN implementation, please refer to git…
Presentation at datafest, May 2019 in Moscow
mai 2019
The presentation starts with a brief introduction of Reinforcement Learning (RL) and an overview of its success. Even though these achievements are compelling, state-of-the-art algorithms require an unreasonable amount of data. Moreover, they sometimes converge to terrible solutions. These restrictions…
Generative Neural Visual Artist (GeNeVA) – Datasets – Generation Code
mai 2019
Scripts to generate the CoDraw and i-CLEVR datasets used for the GeNeVA Neural Visual Artist (GeNeVA) task proposed in Tell, Draw, and Repeat: Generating and modifying images based on continual linguistic instruction.
MS MARCO
mai 2019
MS MARCO is a collection of datasets focused on deep learning in search. The first dataset was a question answering dataset featuring 100,000 real Bing questions and a human generated answer. Since then, we released a 1,000,000-question dataset, a natural…
FigureQA Dataset
mars 2018
Answering questions about a given image is a difficult task, requiring both an understanding of the image and the accompanying query. Microsoft Montreal’s FigureQA dataset introduces a new visual reasoning task for research, specific to graphical plots and figures. The…
Frames Dataset
mars 2018
Frames is a dataset designed to encourage research towards conversational agents which can support decision-making in complex settings, in this case – booking a vacation including flights and a hotel. More than just searching a database, we believe the next…
NewsQA Dataset
mars 2018
The purpose of Microsoft Montreal’s NewsQA dataset is to help the research community build algorithms that are capable of answering questions requiring human-level comprehension and reasoning skills. Leveraging CNN articles from the DeepMind Q&A Dataset, we prepared a crowd-sourced machine…
nlg-eval
janvier 2018
nlg-eval Evaluation code for various unsupervised automated metrics for NLG (Natural Language Generation). It takes as input a hypothesis file, and one or more references files and outputs values of metrics. Rows across these files should correspond to the same…