Ezgi Korkmaz

According to our database, Ezgi Korkmaz authored at least 9 papers between 2021 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

Counteractive RL: Rethinking Core Principles for Efficient and Scalable Deep Reinforcement Learning.

Ezgi Korkmaz

CoRR, March, 2026

Principled Analysis of Deep Reinforcement Learning Evaluation and Design Paradigms.

Ezgi Korkmaz

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2024

A Survey Analyzing Generalization in Deep Reinforcement Learning.

Ezgi Korkmaz

CoRR, 2024

Understanding and Diagnosing Deep Reinforcement Learning.

Ezgi Korkmaz

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023

Detecting Adversarial Directions in Deep Reinforcement Learning to Make Robust Decisions.

Ezgi Korkmaz, Jonah Brown-Cohen

Proceedings of the International Conference on Machine Learning, 2023

Adversarial Robust Deep Reinforcement Learning Requires Redefining Robustness.

Ezgi Korkmaz

Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

2022

Deep Reinforcement Learning Policies Learn Shared Adversarial Features across MDPs.

Ezgi Korkmaz

Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2021

Investigating vulnerabilities of deep neural policies.

Ezgi Korkmaz

Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, 2021

Inaccuracy of State-Action Value Function for Non-Optimal Actions in Adversarially Trained Deep Neural Policies.

Ezgi Korkmaz

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2021