Picture for Yasaman Esfandiari

Yasaman Esfandiari

Cross-Gradient Aggregation for Decentralized Learning from Non-IID data

Add code
Mar 02, 2021
Figure 1 for Cross-Gradient Aggregation for Decentralized Learning from Non-IID data
Figure 2 for Cross-Gradient Aggregation for Decentralized Learning from Non-IID data
Figure 3 for Cross-Gradient Aggregation for Decentralized Learning from Non-IID data
Figure 4 for Cross-Gradient Aggregation for Decentralized Learning from Non-IID data
Viaarxiv icon

Query-based Targeted Action-Space Adversarial Policies on Deep Reinforcement Learning Agents

Add code
Nov 13, 2020
Figure 1 for Query-based Targeted Action-Space Adversarial Policies on Deep Reinforcement Learning Agents
Figure 2 for Query-based Targeted Action-Space Adversarial Policies on Deep Reinforcement Learning Agents
Figure 3 for Query-based Targeted Action-Space Adversarial Policies on Deep Reinforcement Learning Agents
Figure 4 for Query-based Targeted Action-Space Adversarial Policies on Deep Reinforcement Learning Agents
Viaarxiv icon

Robustifying Reinforcement Learning Agents via Action Space Adversarial Training

Add code
Jul 14, 2020
Figure 1 for Robustifying Reinforcement Learning Agents via Action Space Adversarial Training
Figure 2 for Robustifying Reinforcement Learning Agents via Action Space Adversarial Training
Figure 3 for Robustifying Reinforcement Learning Agents via Action Space Adversarial Training
Figure 4 for Robustifying Reinforcement Learning Agents via Action Space Adversarial Training
Viaarxiv icon

A Saddle-Point Dynamical System Approach for Robust Deep Learning

Add code
Oct 18, 2019
Figure 1 for A Saddle-Point Dynamical System Approach for Robust Deep Learning
Figure 2 for A Saddle-Point Dynamical System Approach for Robust Deep Learning
Figure 3 for A Saddle-Point Dynamical System Approach for Robust Deep Learning
Figure 4 for A Saddle-Point Dynamical System Approach for Robust Deep Learning
Viaarxiv icon