Batuhan Yardim
About Me
I am a PhD candidate in Computer Science at ETH Zurich, supervised by Prof. Niao He. My research focuses on the mathemathical theory of reinforcement learning and multi-agent systems, with a focus on mean-field games. I am broadly interested in questions at the intersection of machine learning, optimization, and game theory.
Research
I work on the theory of multi-agent reinforcement learning (focusing on mean-field games and mean-field RL). This includes:
- Fundamental hardness of MF-RL
- Provably efficient algorithms for MARL with many agents
- Connections to game theory, optimization, learning theory.
Publications and Presentations
You can find a full list of my publications on my Google Scholar page.
When is Mean-Field Reinforcement Learning Tractable and Relevant?
Batuhan Yardim, Artur Goldman, Niao He
AAMAS, 2024
Policy Mirror Ascent for Efficient and Independent Learning in Mean Field Games
Batuhan Yardim, Semih Cayci, Mathhieu Geist, Niao He
ICML, 2023
Stateless Mean-Field Games: A Framework for Independent Learning with Large Populations
Batuhan Yardim, Semih Cayci, Niao He
European Workshop on RL (EWRL), 2023
Trust Region Policy Optimization with Optimal Transport Discrepancies: Duality and Algorithm for Continuous Actions
Antonio Terpin, Nicolas Lanzetti, Batuhan Yardim, Florian Dorfler, Giorgia Ramponi
NeurIPS, 2022
On the Statistical Efficiency of Mean-Field Reinforcement Learning with General Function Approximation
Jiawei Huang, Batuhan Yardim, Niao He
AISTATS, 2024
Can Who-Edits-What Predict Edit Survival?
AB Yardim, V Kristof, L Maystre, M Grossglauser
KDD, 2018
Education
PhD in Computer Science
ETH Zürich, Expected graduation: 2025
Advisor: Prof. Niao He
MSc in Electrical Engineering
ETH Zürich, 2020
BSc in Mathematics and Electrical Engineering
Bilkent University, 2018