Andi Nika

PhD Student · MPI-SWS · Saarbrücken, Germany

Andi Nika

I work on reinforcement learning theory, robustness to adversarial attacks in RL, and preference-based reinforcement learning.

Download CV Google Scholar LinkedIn
  • RL theory
  • Adversarial robustness
  • Multi-agent RL
  • Preference-based RL
  • Robustness to data corruption
  • RL for generative AI
  • Multi-armed bandits

About

Short Bio

My name is Andi Nika, and I am a PhD student in the Machine Teaching and Multi-agent Systems groups at MPI-SWS, Saarbrücken, Germany.

I completed my undergraduate degree in Mathematics at the University of Tirana in 2015. Following that, I took a year-long hiatus to explore my artistic passions, participating in The Voice of Albania and reaching the final nights. Afterward, I returned to academia, pursuing graduate degrees in Mathematics and Electrical and Electronics Engineering at Bilkent University, where I developed a strong interest in research in Machine Learning.

Research

Current Interests

Reinforcement learning theory Robustness to adversarial attacks in reinforcement learning Preference-based reinforcement learning Reinforcement learning for fine tuning Multi-agent reinforcement learning Robustness to data corruption in multi-agent reinforcement learning

Publications

Publications and Preprints

* Equal contribution

2026

2025

2024

2023

2021

2020

Contact

Get in touch

Email: andinika@mpi-sws.org

You can also find me on LinkedIn and Google Scholar.