Pegah Alizadeh

News

• Oct 2026New course: Principles of Reinforcement Learning.
• 2026Papers accepted at PAKDD 2026 (meta-RL for energy systems) and IEEE NOMS 2026 (offline RL for network control).
• Jan 2026Théo Zangato defended his PhD, Améliorer la généralisation et la capacité de prévision en apprentissage par renforcement. Congratulations!
• Dec 2025I joined Université Lumière Lyon 2 and the ERIC laboratory as a Junior Professor (CPJ).

Bio

I am a Junior Professor (chaire de professeur junior) at Université Lumière Lyon 2, in the Data Mining and Decision team of the ERIC laboratory. My chair, funded by the French National Research Agency (ANR), studies how to make the alignment of large language models robust, pluralistic and efficient, with applications to digital humanities.

I received my PhD in computer science from Université Sorbonne Paris Nord (formerly Université Paris 13) in 2016, with a thesis on Elicitation and planning in Markov decision processes with unknown rewards. I was then a teaching and research fellow (ATER) at Université Paris Dauphine, and a postdoctoral researcher in the CODAG team of the GREYC laboratory (Université de Caen Normandie) from 2017 to 2018. In 2018, I joined the De Vinci Research Center (Pôle Léonard de Vinci, Paris La Défense), first as a postdoctoral researcher (2018–2019), then as an assistant professor (2019–2022). From 2022 to 2025, I was a Master Researcher at Ericsson, before joining Lyon 2 in December 2025.

Research

My research interests include decision-making, reinforcement learning, and optimization, with a particular focus on robustness and uncertainty quantification and their applications to large language models and networked systems.

I am interested in the alignment and calibration of large language models through pre-training, supervised fine-tuning, and reinforcement learning. I am also interested in studying language models from the perspective of constraints, coordination, and interactions between their different components and agents.

Recent students

PhD students

Master's students

Bachelor's students

Selected publications

2026

• Nicolas Helson, Pegah Alizadeh, Anastasios Giovanidis. Selecting Offline Reinforcement Learning Algorithms for Stochastic Network Control. IEEE NOMS 2026. [arXiv]
• Théo Zangato, Aomar Osmani, Pegah Alizadeh. Meta-RL with Shared Representations Enables Fast Adaptation in Energy Systems. PAKDD 2026. [arXiv]

2025

• Pegah Alizadeh, Anastasios Giovanidis, Pradeepa Ramachandra, Vasileios Koutsoukis, Osama Arouk. Offline Reinforcement Learning for Mobility Robustness Optimization. arXiv preprint, 2025. [arXiv]

2024

• Athanasios Karapantelakis, Pegah Alizadeh, Abdulrahman Alabassi, Kaushik Dey, Alexandros Nikou. Generative AI in mobile networks: a survey. Annals of Telecommunications, 79(1-2): 15-33. [DOI]
• Théo Zangato, Aomar Osmani, Pegah Alizadeh. Enhancing Decision-Making in Energy Management Systems Through Action-Independent Dynamics Learning. ECAI 2024. [DOI]

2023

• Louis Zigrand, Roberto Wolfler Calvo, Emiliano Traversi, Pegah Alizadeh. Optimization-driven Demand Prediction Framework for Suburban Dynamic Demand-Responsive Transport Systems. IJCAI 2023. [DOI]

2022

• Aomar Osmani, Massinissa Hamidi, Pegah Alizadeh. Clustering Approach to Solve Hierarchical Classification Problem Complexity. AAAI 2022. [DOI]
• Pegah Alizadeh, Aomar Osmani, Sammy Taleb. Improving Imitation Learning by Merging Experts Trajectories. CIKM 2022. [DOI]
• Charly Alizadeh, Pegah Alizadeh, Miguel F. Anjos, Lucas Létocart, Emiliano Traversi. How to Learn the Optimal Clique Decompositions in Solving Semidefinite Relaxations for OPF. IJCNN 2022. [DOI]

2021

• Pegah Alizadeh, Emiliano Traversi, Aomar Osmani. Deterministic policies based on maximum regrets in MDPs with imprecise rewards. AI Communications, 34(4): 229-244. [DOI]
• Louis Zigrand, Pegah Alizadeh, Emiliano Traversi, Roberto Wolfler Calvo. Machine Learning Guided Optimization for Demand Responsive Transport Systems. ECML/PKDD 2021. [DOI]

Full list on Google Scholar and DBLP.

Teaching

I teach machine learning and artificial intelligence at the undergraduate and graduate levels. Current courses:

• Principles of Reinforcement Learning (atelier thématique)
• Machine Learning for Textual Data

Service

Reviewing

• Conferences: ICLR 2027, AAAI 2027, ECIR
• Sub-reviewer: IJCAI-ECAI 2018

Program committees

• JFPDA (Journées Francophones sur la Planification, la Décision et l'Apprentissage): 2020 (Angers) and 2022 (Saint-Étienne)
• ECML PKDD 2021
• TALN 2018, Rencontres Jeunes Chercheurs (RJC)

Open positions

Are you a Master's or Bachelor's student interested in machine learning, natural language processing, or reinforcement learning? Research internships are sometimes available. Please contact me with your CV and a few lines on what interests you.

Personal

In my free time, I draw and paint. I read about philosophy and enjoy running and swimming when I can. I also care about environmental and ethical issues.