Picture for Daniel Vial

Daniel Vial

Collaborative Multi-Agent Heterogeneous Multi-Armed Bandits

Add code
May 30, 2023
Viaarxiv icon

Minimax Regret for Cascading Bandits

Add code
Mar 23, 2022
Figure 1 for Minimax Regret for Cascading Bandits
Viaarxiv icon

Robust Multi-Agent Bandits Over Undirected Graphs

Add code
Feb 28, 2022
Figure 1 for Robust Multi-Agent Bandits Over Undirected Graphs
Viaarxiv icon

Improved Algorithms for Misspecified Linear Markov Decision Processes

Add code
Sep 12, 2021
Figure 1 for Improved Algorithms for Misspecified Linear Markov Decision Processes
Viaarxiv icon

Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation

Add code
May 04, 2021
Figure 1 for Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation
Figure 2 for Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation
Viaarxiv icon

One-bit feedback is sufficient for upper confidence bound policies

Add code
Dec 04, 2020
Figure 1 for One-bit feedback is sufficient for upper confidence bound policies
Figure 2 for One-bit feedback is sufficient for upper confidence bound policies
Figure 3 for One-bit feedback is sufficient for upper confidence bound policies
Viaarxiv icon

Robust Multi-Agent Multi-Armed Bandits

Add code
Jul 07, 2020
Figure 1 for Robust Multi-Agent Multi-Armed Bandits
Figure 2 for Robust Multi-Agent Multi-Armed Bandits
Viaarxiv icon

Empirical Policy Evaluation with Supergraphs

Add code
Feb 18, 2020
Figure 1 for Empirical Policy Evaluation with Supergraphs
Figure 2 for Empirical Policy Evaluation with Supergraphs
Viaarxiv icon