Dr Paulo Rauber
Lecturer in Artificial Intelligence
School of Electronic Engineering and Computer Science
Queen Mary University of London
Queen Mary University of London
Research
Artificial Intelligence, Machine Learning, Reinforcement Learning
Interests
I am a lecturer in Artificial Intelligence at Queen Mary University of London. Before becoming a lecturer, I was a postdoctoral researcher in the Swiss AI lab working on reinforcement learning under the supervision of Jürgen Schmidhuber.I believe that intelligence should be defined as a measure of the ability of an agent to achieve goals in a wide range of environments, which makes reinforcement learning an excellent framework to study many challenges that intelligent agents are bound to face.
My current research is focused on developing principled but scalable Bayesian reinforcement learning methods that address the most significant of these challenges: exploration, planning, and generalization.
Publications of specific relevance to the Centre for Multimodal AI
2023
Sasso R, Conserva M and Rauber P (2023). Posterior Sampling for Deep Reinforcement Learning. International Conference on Machine Learning. 01-01-2023
2022
Conserva M and Rauber P (2022). Hardness in Markov Decision Processes: Theory and Practice. Advances in Neural Information Processing Systems. 24-10-2022
Ramesh A, Rauber P, Conserva M and Schmidhuber J (2022). Recurrent Neural-Linear Posterior Sampling
for Nonstationary Contextual Bandits. Neural Computation, Massachusetts Institute of Technology Press vol. 34, 1-41. 09-09-2022
Conserva M and Rauber P (2022). Hardness in Markov Decision Processes: Theory and Practice. Neural Information Processing Systems. 01-01-2022
2021
Rauber P, Ummadisingu A, Mutz F and Schmidhuber J (2021). Reinforcement Learning in Sparse-Reward Environments with Hindsight Policy Gradients. Neural Computation, Massachusetts Institute of Technology Press (MIT Press) 13-05-2021