Picture for Bruno Sinopoli

Bruno Sinopoli

Restless Bandit Problem with Rewards Generated by a Linear Gaussian Dynamical System

Add code
May 15, 2024
Viaarxiv icon

Beyond PCA: A Probabilistic Gram-Schmidt Approach to Feature Extraction

Add code
Nov 15, 2023
Viaarxiv icon

Towards Hyperparameter-Agnostic DNN Training via Dynamical System Insights

Add code
Oct 21, 2023
Viaarxiv icon

Model-Free Learning and Optimal Policy Design in Multi-Agent MDPs Under Probabilistic Agent Dropout

Add code
Apr 24, 2023
Viaarxiv icon

Stochastic Multi-armed Bandits with Non-stationary Rewards Generated by a Linear Dynamical System

Add code
Apr 06, 2022
Figure 1 for Stochastic Multi-armed Bandits with Non-stationary Rewards Generated by a Linear Dynamical System
Figure 2 for Stochastic Multi-armed Bandits with Non-stationary Rewards Generated by a Linear Dynamical System
Figure 3 for Stochastic Multi-armed Bandits with Non-stationary Rewards Generated by a Linear Dynamical System
Viaarxiv icon

Toward Safe and Efficient Human-Robot Interaction via Behavior-Driven Danger Signaling

Add code
Feb 11, 2021
Figure 1 for Toward Safe and Efficient Human-Robot Interaction via Behavior-Driven Danger Signaling
Figure 2 for Toward Safe and Efficient Human-Robot Interaction via Behavior-Driven Danger Signaling
Figure 3 for Toward Safe and Efficient Human-Robot Interaction via Behavior-Driven Danger Signaling
Figure 4 for Toward Safe and Efficient Human-Robot Interaction via Behavior-Driven Danger Signaling
Viaarxiv icon

Kalman Filtering with Intermittent Observations: Weak Convergence to a Stationary Distribution

Add code
May 28, 2010
Figure 1 for Kalman Filtering with Intermittent Observations: Weak Convergence to a Stationary Distribution
Figure 2 for Kalman Filtering with Intermittent Observations: Weak Convergence to a Stationary Distribution
Viaarxiv icon