Picture for Marc Abeille

Marc Abeille

CEREMADE

Near-continuous time Reinforcement Learning for continuous state-action spaces

Add code
Sep 06, 2023
Viaarxiv icon

Jointly Efficient and Optimal Algorithms for Logistic Bandits

Add code
Jan 19, 2022
Figure 1 for Jointly Efficient and Optimal Algorithms for Logistic Bandits
Figure 2 for Jointly Efficient and Optimal Algorithms for Logistic Bandits
Figure 3 for Jointly Efficient and Optimal Algorithms for Logistic Bandits
Viaarxiv icon

Regret Bounds for Generalized Linear Bandits under Parameter Drift

Add code
Mar 09, 2021
Figure 1 for Regret Bounds for Generalized Linear Bandits under Parameter Drift
Figure 2 for Regret Bounds for Generalized Linear Bandits under Parameter Drift
Viaarxiv icon

Instance-Wise Minimax-Optimal Algorithms for Logistic Bandits

Add code
Oct 23, 2020
Figure 1 for Instance-Wise Minimax-Optimal Algorithms for Logistic Bandits
Figure 2 for Instance-Wise Minimax-Optimal Algorithms for Logistic Bandits
Figure 3 for Instance-Wise Minimax-Optimal Algorithms for Logistic Bandits
Figure 4 for Instance-Wise Minimax-Optimal Algorithms for Logistic Bandits
Viaarxiv icon

Real-Time Optimisation for Online Learning in Auctions

Add code
Oct 20, 2020
Figure 1 for Real-Time Optimisation for Online Learning in Auctions
Figure 2 for Real-Time Optimisation for Online Learning in Auctions
Figure 3 for Real-Time Optimisation for Online Learning in Auctions
Figure 4 for Real-Time Optimisation for Online Learning in Auctions
Viaarxiv icon

Efficient Optimistic Exploration in Linear-Quadratic Regulators via Lagrangian Relaxation

Add code
Jul 13, 2020
Figure 1 for Efficient Optimistic Exploration in Linear-Quadratic Regulators via Lagrangian Relaxation
Figure 2 for Efficient Optimistic Exploration in Linear-Quadratic Regulators via Lagrangian Relaxation
Figure 3 for Efficient Optimistic Exploration in Linear-Quadratic Regulators via Lagrangian Relaxation
Figure 4 for Efficient Optimistic Exploration in Linear-Quadratic Regulators via Lagrangian Relaxation
Viaarxiv icon

Improved Optimistic Algorithms for Logistic Bandits

Add code
Feb 18, 2020
Figure 1 for Improved Optimistic Algorithms for Logistic Bandits
Figure 2 for Improved Optimistic Algorithms for Logistic Bandits
Figure 3 for Improved Optimistic Algorithms for Logistic Bandits
Viaarxiv icon

Thompson Sampling in Non-Episodic Restless Bandits

Add code
Oct 12, 2019
Figure 1 for Thompson Sampling in Non-Episodic Restless Bandits
Figure 2 for Thompson Sampling in Non-Episodic Restless Bandits
Figure 3 for Thompson Sampling in Non-Episodic Restless Bandits
Viaarxiv icon

Linear Thompson Sampling Revisited

Add code
Mar 27, 2017
Figure 1 for Linear Thompson Sampling Revisited
Figure 2 for Linear Thompson Sampling Revisited
Figure 3 for Linear Thompson Sampling Revisited
Viaarxiv icon

Thompson Sampling for Linear-Quadratic Control Problems

Add code
Mar 27, 2017
Figure 1 for Thompson Sampling for Linear-Quadratic Control Problems
Figure 2 for Thompson Sampling for Linear-Quadratic Control Problems
Viaarxiv icon