Picture for Yann Ollivier

Yann Ollivier

FAIR

Simple Ingredients for Offline Reinforcement Learning

Add code
Mar 19, 2024
Figure 1 for Simple Ingredients for Offline Reinforcement Learning
Figure 2 for Simple Ingredients for Offline Reinforcement Learning
Figure 3 for Simple Ingredients for Offline Reinforcement Learning
Figure 4 for Simple Ingredients for Offline Reinforcement Learning
Viaarxiv icon

Does Zero-Shot Reinforcement Learning Exist?

Add code
Sep 29, 2022
Figure 1 for Does Zero-Shot Reinforcement Learning Exist?
Figure 2 for Does Zero-Shot Reinforcement Learning Exist?
Figure 3 for Does Zero-Shot Reinforcement Learning Exist?
Figure 4 for Does Zero-Shot Reinforcement Learning Exist?
Viaarxiv icon

Agnostic Physics-Driven Deep Learning

May 30, 2022
Figure 1 for Agnostic Physics-Driven Deep Learning
Figure 2 for Agnostic Physics-Driven Deep Learning
Figure 3 for Agnostic Physics-Driven Deep Learning
Figure 4 for Agnostic Physics-Driven Deep Learning
Viaarxiv icon

Unbiased Methods for Multi-Goal Reinforcement Learning

Jun 16, 2021
Figure 1 for Unbiased Methods for Multi-Goal Reinforcement Learning
Figure 2 for Unbiased Methods for Multi-Goal Reinforcement Learning
Viaarxiv icon

Learning One Representation to Optimize All Rewards

Add code
Mar 14, 2021
Figure 1 for Learning One Representation to Optimize All Rewards
Figure 2 for Learning One Representation to Optimize All Rewards
Figure 3 for Learning One Representation to Optimize All Rewards
Figure 4 for Learning One Representation to Optimize All Rewards
Viaarxiv icon

Learning Successor States and Goal-Dependent Values: A Mathematical Viewpoint

Jan 18, 2021
Figure 1 for Learning Successor States and Goal-Dependent Values: A Mathematical Viewpoint
Viaarxiv icon

Convergence of Online Adaptive and Recurrent Optimization Algorithms

May 12, 2020
Viaarxiv icon

Interpreting a Penalty as the Influence of a Bayesian Prior

Feb 01, 2020
Figure 1 for Interpreting a Penalty as the Influence of a Bayesian Prior
Figure 2 for Interpreting a Penalty as the Influence of a Bayesian Prior
Figure 3 for Interpreting a Penalty as the Influence of a Bayesian Prior
Viaarxiv icon

White-box vs Black-box: Bayes Optimal Strategies for Membership Inference

Aug 29, 2019
Figure 1 for White-box vs Black-box: Bayes Optimal Strategies for Membership Inference
Figure 2 for White-box vs Black-box: Bayes Optimal Strategies for Membership Inference
Figure 3 for White-box vs Black-box: Bayes Optimal Strategies for Membership Inference
Figure 4 for White-box vs Black-box: Bayes Optimal Strategies for Membership Inference
Viaarxiv icon

Separating value functions across time-scales

Add code
Feb 08, 2019
Figure 1 for Separating value functions across time-scales
Figure 2 for Separating value functions across time-scales
Figure 3 for Separating value functions across time-scales
Figure 4 for Separating value functions across time-scales
Viaarxiv icon