 Learning Transferable Domain Priors for Safe Exploration in
Reinforcement LearningIEEE International Joint Conference on Neural Network (IJCNN), 2019 |
 Diversity-Inducing Policy Gradient: Using Maximum Mean Discrepancy to
Find a Set of Diverse PoliciesInternational Joint Conference on Artificial Intelligence (IJCAI), 2019 M. A. Masood Finale Doshi-Velez |
 Smoothing Policies and Safe Policy GradientsMachine-mediated learning (ML), 2019 |
 Diverse Exploration via Conjugate Policies for Policy Gradient MethodsAAAI Conference on Artificial Intelligence (AAAI), 2019 |