5 citations · 8 across the 8 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
cs.LG2021★ 1 cited
Deep Reinforcement Learning Policies Learn Shared Adversarial Features Across MDPs
Ezgi Korkmaz
The use of deep neural networks as function approximators has led to striking progress for reinforcement learning algorithms and applications. Yet the knowledge we have on decision…
cs.LG2021★ 5 cited
Investigating Vulnerabilities of Deep Neural Policies
Ezgi Korkmaz
Reinforcement learning policies based on deep neural networks are vulnerable to imperceptible adversarial perturbations to their inputs, in much the same way as neural network imag…