Picture for Andras Gyorgy

Andras Gyorgy

A New Look at Dynamic Regret for Non-Stationary Stochastic Bandits

Jan 17, 2022
Viaarxiv icon

Learning to Minimize Age of Information over an Unreliable Channel with Energy Harvesting

Jun 30, 2021
Figure 1 for Learning to Minimize Age of Information over an Unreliable Channel with Energy Harvesting
Figure 2 for Learning to Minimize Age of Information over an Unreliable Channel with Energy Harvesting
Figure 3 for Learning to Minimize Age of Information over an Unreliable Channel with Energy Harvesting
Figure 4 for Learning to Minimize Age of Information over an Unreliable Channel with Energy Harvesting
Viaarxiv icon

On Multi-objective Policy Optimization as a Tool for Reinforcement Learning

Jun 15, 2021
Figure 1 for On Multi-objective Policy Optimization as a Tool for Reinforcement Learning
Figure 2 for On Multi-objective Policy Optimization as a Tool for Reinforcement Learning
Figure 3 for On Multi-objective Policy Optimization as a Tool for Reinforcement Learning
Figure 4 for On Multi-objective Policy Optimization as a Tool for Reinforcement Learning
Viaarxiv icon

Defending Against Image Corruptions Through Adversarial Augmentations

Add code
Apr 20, 2021
Figure 1 for Defending Against Image Corruptions Through Adversarial Augmentations
Figure 2 for Defending Against Image Corruptions Through Adversarial Augmentations
Figure 3 for Defending Against Image Corruptions Through Adversarial Augmentations
Figure 4 for Defending Against Image Corruptions Through Adversarial Augmentations
Viaarxiv icon

A Reinforcement Learning Approach to Age of Information in Multi-User Networks with HARQ

Feb 19, 2021
Figure 1 for A Reinforcement Learning Approach to Age of Information in Multi-User Networks with HARQ
Figure 2 for A Reinforcement Learning Approach to Age of Information in Multi-User Networks with HARQ
Figure 3 for A Reinforcement Learning Approach to Age of Information in Multi-User Networks with HARQ
Figure 4 for A Reinforcement Learning Approach to Age of Information in Multi-User Networks with HARQ
Viaarxiv icon

Perceptually Constrained Adversarial Attacks

Feb 14, 2021
Figure 1 for Perceptually Constrained Adversarial Attacks
Figure 2 for Perceptually Constrained Adversarial Attacks
Figure 3 for Perceptually Constrained Adversarial Attacks
Figure 4 for Perceptually Constrained Adversarial Attacks
Viaarxiv icon

Non-Stationary Bandits with Intermediate Observations

Jun 03, 2020
Figure 1 for Non-Stationary Bandits with Intermediate Observations
Figure 2 for Non-Stationary Bandits with Intermediate Observations
Figure 3 for Non-Stationary Bandits with Intermediate Observations
Figure 4 for Non-Stationary Bandits with Intermediate Observations
Viaarxiv icon

Communication without Interception: Defense against Deep-Learning-based Modulation Detection

Feb 27, 2019
Figure 1 for Communication without Interception: Defense against Deep-Learning-based Modulation Detection
Figure 2 for Communication without Interception: Defense against Deep-Learning-based Modulation Detection
Figure 3 for Communication without Interception: Defense against Deep-Learning-based Modulation Detection
Figure 4 for Communication without Interception: Defense against Deep-Learning-based Modulation Detection
Viaarxiv icon

Learning from Delayed Outcomes with Intermediate Observations

Jul 24, 2018
Figure 1 for Learning from Delayed Outcomes with Intermediate Observations
Figure 2 for Learning from Delayed Outcomes with Intermediate Observations
Figure 3 for Learning from Delayed Outcomes with Intermediate Observations
Figure 4 for Learning from Delayed Outcomes with Intermediate Observations
Viaarxiv icon

Detection of Adversarial Training Examples in Poisoning Attacks through Anomaly Detection

Add code
Feb 08, 2018
Figure 1 for Detection of Adversarial Training Examples in Poisoning Attacks through Anomaly Detection
Figure 2 for Detection of Adversarial Training Examples in Poisoning Attacks through Anomaly Detection
Figure 3 for Detection of Adversarial Training Examples in Poisoning Attacks through Anomaly Detection
Figure 4 for Detection of Adversarial Training Examples in Poisoning Attacks through Anomaly Detection
Viaarxiv icon