Picture for Alessandro Lazaric

Alessandro Lazaric

INRIA Lille - Nord Europe

System-2 Recommenders: Disentangling Utility and Engagement in Recommendation Systems via Temporal Point-Processes

May 29, 2024
Viaarxiv icon

Reinforcement Learning with Options and State Representation

Mar 25, 2024
Figure 1 for Reinforcement Learning with Options and State Representation
Figure 2 for Reinforcement Learning with Options and State Representation
Figure 3 for Reinforcement Learning with Options and State Representation
Figure 4 for Reinforcement Learning with Options and State Representation
Viaarxiv icon

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

Layered State Discovery for Incremental Autonomous Exploration

Feb 07, 2023
Figure 1 for Layered State Discovery for Incremental Autonomous Exploration
Figure 2 for Layered State Discovery for Incremental Autonomous Exploration
Viaarxiv icon

Learning Goal-Conditioned Policies Offline with Self-Supervised Reward Shaping

Add code
Jan 05, 2023
Figure 1 for Learning Goal-Conditioned Policies Offline with Self-Supervised Reward Shaping
Figure 2 for Learning Goal-Conditioned Policies Offline with Self-Supervised Reward Shaping
Figure 3 for Learning Goal-Conditioned Policies Offline with Self-Supervised Reward Shaping
Figure 4 for Learning Goal-Conditioned Policies Offline with Self-Supervised Reward Shaping
Viaarxiv icon

On the Complexity of Representation Learning in Contextual Linear Bandits

Dec 19, 2022
Figure 1 for On the Complexity of Representation Learning in Contextual Linear Bandits
Viaarxiv icon

Improved Adaptive Algorithm for Scalable Active Learning with Weak Labeler

Nov 04, 2022
Figure 1 for Improved Adaptive Algorithm for Scalable Active Learning with Weak Labeler
Figure 2 for Improved Adaptive Algorithm for Scalable Active Learning with Weak Labeler
Figure 3 for Improved Adaptive Algorithm for Scalable Active Learning with Weak Labeler
Figure 4 for Improved Adaptive Algorithm for Scalable Active Learning with Weak Labeler
Viaarxiv icon

Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees

Oct 24, 2022
Figure 1 for Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees
Figure 2 for Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees
Figure 3 for Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees
Figure 4 for Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees
Viaarxiv icon

Contextual bandits with concave rewards, and an application to fair ranking

Oct 18, 2022
Figure 1 for Contextual bandits with concave rewards, and an application to fair ranking
Figure 2 for Contextual bandits with concave rewards, and an application to fair ranking
Figure 3 for Contextual bandits with concave rewards, and an application to fair ranking
Figure 4 for Contextual bandits with concave rewards, and an application to fair ranking
Viaarxiv icon

Reaching Goals is Hard: Settling the Sample Complexity of the Stochastic Shortest Path

Oct 10, 2022
Figure 1 for Reaching Goals is Hard: Settling the Sample Complexity of the Stochastic Shortest Path
Figure 2 for Reaching Goals is Hard: Settling the Sample Complexity of the Stochastic Shortest Path
Figure 3 for Reaching Goals is Hard: Settling the Sample Complexity of the Stochastic Shortest Path
Viaarxiv icon