Picture for Nima Akbarzadeh

Nima Akbarzadeh

Approximate information state based convergence analysis of recurrent Q-learning

Add code
Jun 09, 2023
Figure 1 for Approximate information state based convergence analysis of recurrent Q-learning
Figure 2 for Approximate information state based convergence analysis of recurrent Q-learning
Figure 3 for Approximate information state based convergence analysis of recurrent Q-learning
Figure 4 for Approximate information state based convergence analysis of recurrent Q-learning
Viaarxiv icon

On learning Whittle index policy for restless bandits with scalable regret

Feb 07, 2022
Figure 1 for On learning Whittle index policy for restless bandits with scalable regret
Figure 2 for On learning Whittle index policy for restless bandits with scalable regret
Figure 3 for On learning Whittle index policy for restless bandits with scalable regret
Viaarxiv icon

Scalable Operator Allocation for Multi-Robot Assistance: A Restless Bandit Approach

Nov 11, 2021
Figure 1 for Scalable Operator Allocation for Multi-Robot Assistance: A Restless Bandit Approach
Figure 2 for Scalable Operator Allocation for Multi-Robot Assistance: A Restless Bandit Approach
Figure 3 for Scalable Operator Allocation for Multi-Robot Assistance: A Restless Bandit Approach
Figure 4 for Scalable Operator Allocation for Multi-Robot Assistance: A Restless Bandit Approach
Viaarxiv icon

Gambler's Ruin Bandit Problem

Sep 29, 2016
Figure 1 for Gambler's Ruin Bandit Problem
Figure 2 for Gambler's Ruin Bandit Problem
Figure 3 for Gambler's Ruin Bandit Problem
Figure 4 for Gambler's Ruin Bandit Problem
Viaarxiv icon