Ariel Kwiatkowski
Scholar

Ariel Kwiatkowski

Google Scholar ID: xkhji7MAAAAJ
Meta AI
reinforcement learningartificial intelligenceAI safetyCrowd Simulation
Citations & Impact
All-time
Citations
1,090
 
H-index
5
 
i10-index
3
 
Publications
15
 
Co-authors
0
 
Resume (English only)
Academic Achievements
  • - Published papers such as 'Why there's no multiagent policy gradient theorem'
  • - Maintained several open-source projects like Gymnasium
Research Experience
  • - Research Engineer at Meta AI
  • - Worked at AI Redefined, building tooling for human-in-the-loop RL
  • - Maintainer of Gymnasium (the official continuation of OpenAI Gym), contributor to PettingZoo, SuperSuit, and other Farama Foundation projects
Education
  • - PhD in Artificial Intelligence from École Polytechnique
  • - MSc in Autonomous Systems from KTH Royal Institute of Technology & Aalto University
  • - BSc in Physics from University of Warsaw
Background
  • AI researcher (officially Research Engineer) at Meta. Until recently, working at AI Redefined building tooling for human-in-the-loop RL. Interests include Artificial Intelligence, Reinforcement Learning, and AI Alignment.
Miscellany
  • Erdős number <= 4
Co-authors
0 total
Co-authors: 0 (list not available)