Paul Chambaz

Hey! I’m a Master’s 2 student in Computer Science (AI2D track) at Sorbonne Université. I’m interested in reinforcement learning because it can achieve incredible performance in real-world tasks, yet we still don’t understand why many algorithms work or fail. I recently researched estimation bias in RL with Prof. Olivier Sigaud at ISIR. I believe in transparent, controllable AI rather than closed black boxes. Outside of my studies, I’m bouldering or developing open-source tools for ALIAS, including a hackathon organization platform for CS student associations.

profile picture

Research

Actor Free critic Updates for Off-Policy and Offline Learning
Paul Chambaz, Frédéric Li Combeau
M1 AI2D Sorbonne Université

Blog posts

Some notes on the TQC figure (Aug 2025)

Estimation biases represent a persistent challenge in reinforcement learning, where errors in value estimation can accumulate through bootstrapping and compromise learning efficiency. Among these …

Projects

Polybase - student paper handout distribution system
ALIAS Student Association
go, templ, htmx, tailwindcss, sqlite3
Mpcube - album focused terminal music client
paulchambaz
go, bubbletea, mpd

Education

Master in Computer Science - AI2D
Sorbonne Université (2024-2026)
M1: 16.4/20 1st/53, S1: 15.85/20, S2: 17.03/20
Excellence diploma program
Bachelor in Computer Science
Université Paris Cité (2019-2023)
Mention Très Bien - 16/20
First year bachelor Computer Science
Université Claude Bernard Lyon 1 (2018-2019)

Work Experience

Research Intern
ISIR Laboratory, Sorbonne Université (Summer 2024)
Supervised by Prof. Olivier Sigaud
Python, JAX, Pytorch, Reinforcement Learning, Matplotlib
Cybersecurity Developer
Mobeta (February - August 2024)
Supervised by Arthur Le Corguillé
TypeScript, Go, Python, Docker, Cybersecurity
OSINT Developer Intern
Lexfo (Summer 2023)
Supervised by Armand Sylvain
Python, Ansible, Active Directory, Proxmox

Coursework

M1 Sorbonne Université (S2)

MU4IN204 - Decision and Games (92.5/100)
MU4IN201 - Problem Solving (95/100)
MU4IN202 - Foundations of Multi-agent Systems (84.4/100)
MU4IN811 - Machine Learning (63.35/100)
MU4IN206 - AI2D Research and Development Project (91/100)
MU4IN207 - Learning and Robotics (85/100)

M1 Sorbonne Université (S1)

MU4IN800 - Logic and Knowledge Representations (89.5/100)
MU4IN601 - Probabilistic and Statistical Methods and Algorithms for Computer Science (92.2/100)
MU4IN200 - Modeling, Optimization, Graphs, and Linear Programming (71/100)
MU4IN600 - Basics of Image Processing (75.35/100)
MU4IN900 - Complexity, Randomized and Approximate Algorithms (68/100)
MU4IN400 - Concurrent and Distributed System Programming (96/100)