Publications

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret. Emilio Jorge, Christos Dimitrakakis, Debabrota Basu. In submission, previously at EWRL 2024.

Minimax-bayes reinforcement learning. Thomas Kleine Buening*, Christos Dimitrakakis*, Hannes Eriksson*, Divya Grover*, Emilio Jorge*. AISTATS 2023.

Spectral Analysis of Kernel and Neural Embeddings: Optimization and Generalization. Arman Rahbar, Emilio Jorge, Morteza Haghir Chehreghani, Devdatt Dubhashi. Neural Processing Letters 55 2023.

Inferential Induction: Joint Bayesian Estimation of MDPs and Value Functions. Emilio Jorge*, Hannes Eriksson*, Christos Dimitrakakis*, Debabrota Basu, Divya Grover. Contributed talk [video] at ICBINB Workshop@NeurIPS 2020.

Learning to Play Guess Who? and Inventing a Grounded Language as a Consequence. Emilio Jorge, Mikael Kågebäck, Fredrik D. Johansson, Emil Gustavsson. Presented at Deep Reinforcement Learning Workshop at NeurIPS 2016.

BAgger: A Bayesian Algorithm for Safe and Query-efficient Imitation Learning. Constantin Cronrath, Emilio Jorge, John Moberg et al. Presented at International Conference on Intelligent Robots and Systems (IROS) 2018 workshop on Machine Learning in Robot Motion Planning.

Reinforcement learning in real-time geometry assurance. Emilio Jorge, Lucas Brynte, Constantin Cronrath et al. 51st CIRP Conference on Manufacturing Systems (CIRP CMS 2018).

*, Equal contribution

Presentations

Introduction to Normalizing flows on October 10 2019 at RISE AI, Gothenburg.

Posters

Exploration and uncertainty in generative networks for reinforcement learning PhD project overview poster. Presented at German universities and Max Planck institutes during WASP study trip in October 2019.