← Search

Pinar Ozisik

1 accepted papers

2020

Security Analysis of Safe and Seldonian Reinforcement Learning Algorithms

NeurIPS 2020poster

We analyze the extent to which existing methods rely on accurate training data for a specific class of reinforcement learning (RL) algorithms, known as Safe and Seldonian RL. We introduce a new measure of security to quantify the susceptibility to perturbations in training data by creating an attack…