Raphael Avalos

Raphael Avalos

PhD Candidate

AI Lab VUB

Biography

Hello! I am a PhD student at the AI LAB of the VUB (University of Brussels) under the supervision of Ann Nowe and Diederik Roijers. My research focuses mostly on collaborative multi-agent reinforcement learning with the goal of learning better and most robust policies that can be ultimately deployed in the real world. During my PhD I plan to target this problem by learning how the agents can communicate in a possibly limited bandwidth setting, and by developing new exploration strategies. I am also working on partially observable single-agent RL, multi-agent bandits and genetic inspired evolution. Fell free to contact me !

Download my resumé.

Interests
  • Artificial Intelligence
  • Reinforcement Learning
  • Partially Observable
  • Multi-Agent
  • Collaboration
  • Communication
  • Exploration
  • VAE
Education

  • MSc in Applied Mathematics for AI, 2019

    Ecole Normale Superieur de Cachan

  • MSE in Computer Science, 2019

    Telecom Paris

Experience

 
 
 
 
 
Vrije Universiteit Brussel (VUB) - AI Lab - FWO
PhD Candidate
Vrije Universiteit Brussel (VUB) - AI Lab - FWO
May 2020 – Present Brussels, Belgium
PhD supervised by Prof. Ann Nowe and Dr. Diederik Roijers.
 
 
 
 
 
Vrije Universiteit Brussel (VUB) - AI Lab
Research Intern
Vrije Universiteit Brussel (VUB) - AI Lab
Jan 2020 – Apr 2020 Brussels, Belgium
Working on Multi-agent Reinforcement Learning under the supervision of Prof. Ann Nowe.
 
 
 
 
 
INRIA - SequeL Team (now Scool)
Research Intern
INRIA - SequeL Team (now Scool)
Apr 2019 – Oct 2019 Lille, France
Worked on Hierarchical Reinforcement Learning (HRL) applied to the Rubik’s Cube under the supervision Dr. Florian Strub and Prof. Philippe Preux.

Accomplish­ments

PhD Fellowship fundamental research
FWO - Research Foundation - Flanders Oct 2020 – Sep 2024

Publications Conference

Raphael Avalos (2022). Exploration and Communication for Partially Observable Collaborative Multi-Agent Reinforcement Learning. AAMAS 2022.

PDF Cite

Raphael Avalos, Mathieu Reymond, Ann Nowe, Diederik M. Roijers (2022). Local Advantage Networks for Cooperative Multi-Agent Reinforcement Learning. AAMAS 2022.

PDF Cite

Publications Workshop

Raphael Avalos, Mathieu Reymond, Ann Nowe, Diederik M. Roijers (2022). Local Advantage Networks for Multi-Agent Reinforcement Learning in Dec-POMDPs. EWRL 2022.

PDF Cite

Andries Rosseau, Raphael Avalos, Ann Nowe (2022). Autocurricula and Emergent Sociality from a Gene Perspective. ALA 2022 (AAMAS Workshop).

PDF Cite Video

Eugenio Bargiacchi, Raphael Avalos, Timothy Verstraeten, Pieter Libin, Ann Nowe, Diederik M. Roijers (2022). Multi-agent RMax for Multi-Agent Multi-Armed Bandits. ALA 2022 (AAMAS Workshop).

PDF Cite Video

Contact