Why there's no multiagent policy gradient theorem
I present a derivation of the policy gradient theorem for homogeneous multiagent RL systems. The results are… boring.
▶️About Me
AI researcher, waiting to start my new position very soon. Until recently, I was working at AI Redefined where I’m building tooling for human-in-the-loop RL. I got my PhD from École Polytechnique, my thesis topic was “Simulating Crowds with Reinforcement Learning”. In the past I was at University of Warsaw, KTH Royal Institute of Technology, and Aalto University.
In my free time, I’m the maintainer of Gymnasium (the official continuation of OpenAI Gym), sometimes reviewing other people’s bugs, sometimes adding my own bugs… I mean, features. Sometimes I also help with PettingZoo, SuperSuit and other projects in the Farama Foundation.
Erdős number <= 4
Interests
- Artificial Intelligence
- Reinforcement Learning
- AI Alignment
Education
PhD Artificial Intelligence
École Polytechnique
MSc Autonomous Systems
KTH Royal Institute of Technology & Aalto University
BSc Physics
University of Warsaw
Recent Posts
Advent of Code 2020 with Haskell
An ongoing documentation of my implementations of Advent of Code 2020
Creating a personal website: a short practical guide
I describe the process of making this exact website - to help avoid some frustrations I encountered along the way.
AI cannot be apolitical
AI enthusiast seems to believe that being apolitical is a virtue for the sake of Science. Spoiler: it’s not.