Research

My main research interests are:

• Model Based Reinforcement Learning

• Novelty Search and Quality Diversity Algorithms

• AI Embodiement and the study of Emergent behaviors

Research activities

•  Co-organizer of the Evolutionary RL workshop at GECCO 2021 and 2022 

• Invited guest editor of the “Evolutionary Reinforcement Learning” Special Issue for the ACM TELO journal.

The complete list of my publications can be found on one of these sites:

• Google Scholar 

• ArXiv 

• dblp 

Selected Publications

• G. Paolo, J. Gonzalez-Billandon, B. Kégl, "A Call for Embodied AI", Submitted to ICML 2024 Position paper track, ArXiv link 

• G. Paolo, "Learning in Sparse Rewards settings through Quality-Diversity algorithms", 2022, ArXiv link, PhD Thesis

• G. Paolo, A. Coninx, A. Laflaquière, S. Doncieux, "Discovering and Exploiting Sparse Rewards in a Learned Behavior Space", Evolutionary Computation Journal MIT Press, 2024, ArXiv link 

• G. Paolo, A. Coninx, S. Doncieux, A. Laflaquière, "Sparse Reward Exploration via Novelty Search and Emitters", The Genetic and Evolutionary Computation Conference (GECCO) 2021, ArXiv link. Nominated for best paper award in the CS track.

• G. Paolo, A. Laflaquière, A. Coninx, S. Doncieux, "Unsupervised Learning and Exploration of Reachable Outcome Space", 2020 IEEE International Conference on Robotics and Automation (ICRA), ArXiv link

• L. Tai, G. Paolo, M. Liu, "Virtual-to-real deep reinforcement learning: Continuous control of mobile robots for mapless navigation", 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) , ArXiv link