Picture for Tanguy Urvoy

Tanguy Urvoy

FT R and D

Under the Hood of Tabular Data Generation Models: the Strong Impact of Hyperparameter Tuning

Add code
Jun 18, 2024
Figure 1 for Under the Hood of Tabular Data Generation Models: the Strong Impact of Hyperparameter Tuning
Figure 2 for Under the Hood of Tabular Data Generation Models: the Strong Impact of Hyperparameter Tuning
Figure 3 for Under the Hood of Tabular Data Generation Models: the Strong Impact of Hyperparameter Tuning
Figure 4 for Under the Hood of Tabular Data Generation Models: the Strong Impact of Hyperparameter Tuning
Viaarxiv icon

Few-Shot Structured Policy Learning for Multi-Domain and Multi-Task Dialogues

Add code
Feb 22, 2023
Viaarxiv icon

Graph Neural Network Policies and Imitation Learning for Multi-Domain Task-Oriented Dialogues

Add code
Oct 11, 2022
Figure 1 for Graph Neural Network Policies and Imitation Learning for Multi-Domain Task-Oriented Dialogues
Figure 2 for Graph Neural Network Policies and Imitation Learning for Multi-Domain Task-Oriented Dialogues
Figure 3 for Graph Neural Network Policies and Imitation Learning for Multi-Domain Task-Oriented Dialogues
Figure 4 for Graph Neural Network Policies and Imitation Learning for Multi-Domain Task-Oriented Dialogues
Viaarxiv icon

Denoising Pre-Training and Data Augmentation Strategies for Enhanced RDF Verbalization with Transformers

Add code
Dec 01, 2020
Figure 1 for Denoising Pre-Training and Data Augmentation Strategies for Enhanced RDF Verbalization with Transformers
Figure 2 for Denoising Pre-Training and Data Augmentation Strategies for Enhanced RDF Verbalization with Transformers
Viaarxiv icon

Diluted Near-Optimal Expert Demonstrations for Guiding Dialogue Stochastic Policy Optimisation

Add code
Nov 25, 2020
Figure 1 for Diluted Near-Optimal Expert Demonstrations for Guiding Dialogue Stochastic Policy Optimisation
Figure 2 for Diluted Near-Optimal Expert Demonstrations for Guiding Dialogue Stochastic Policy Optimisation
Figure 3 for Diluted Near-Optimal Expert Demonstrations for Guiding Dialogue Stochastic Policy Optimisation
Figure 4 for Diluted Near-Optimal Expert Demonstrations for Guiding Dialogue Stochastic Policy Optimisation
Viaarxiv icon

Scaling up budgeted reinforcement learning

Add code
Mar 06, 2019
Figure 1 for Scaling up budgeted reinforcement learning
Figure 2 for Scaling up budgeted reinforcement learning
Figure 3 for Scaling up budgeted reinforcement learning
Figure 4 for Scaling up budgeted reinforcement learning
Viaarxiv icon

Corrupt Bandits for Preserving Local Privacy

Add code
Nov 02, 2017
Figure 1 for Corrupt Bandits for Preserving Local Privacy
Figure 2 for Corrupt Bandits for Preserving Local Privacy
Figure 3 for Corrupt Bandits for Preserving Local Privacy
Figure 4 for Corrupt Bandits for Preserving Local Privacy
Viaarxiv icon

Random Forest for the Contextual Bandit Problem - extended version

Add code
Sep 15, 2016
Figure 1 for Random Forest for the Contextual Bandit Problem - extended version
Figure 2 for Random Forest for the Contextual Bandit Problem - extended version
Figure 3 for Random Forest for the Contextual Bandit Problem - extended version
Figure 4 for Random Forest for the Contextual Bandit Problem - extended version
Viaarxiv icon

Bandit Structured Prediction for Learning from Partial Feedback in Statistical Machine Translation

Add code
Jan 18, 2016
Figure 1 for Bandit Structured Prediction for Learning from Partial Feedback in Statistical Machine Translation
Figure 2 for Bandit Structured Prediction for Learning from Partial Feedback in Statistical Machine Translation
Viaarxiv icon

A Relative Exponential Weighing Algorithm for Adversarial Utility-based Dueling Bandits

Add code
Jan 15, 2016
Figure 1 for A Relative Exponential Weighing Algorithm for Adversarial Utility-based Dueling Bandits
Figure 2 for A Relative Exponential Weighing Algorithm for Adversarial Utility-based Dueling Bandits
Figure 3 for A Relative Exponential Weighing Algorithm for Adversarial Utility-based Dueling Bandits
Figure 4 for A Relative Exponential Weighing Algorithm for Adversarial Utility-based Dueling Bandits
Viaarxiv icon