Roger Creus Castanyer

Research MSc student @ Mila / UdeM

About me

I am 22 years old, I am from Barcelona and I graduated in the BSc in Data Science and Engineering at the Universitat Politècnica de Catalunya (UPC) in Barcelona, Spain. I am a Research MSc student at Mila Québec & at University of Montréal since Fall 2022. I have joined the Robotics and Embodied AI Lab (REAL) under supervision of Professor Glen Berseth.


My research interests are primarily focused on reinforcement learning and deep learning. I rely on a solid basis in the mathematical foundations of algebra, calculus, optimization, information theory and machine learning. My long-term research goal is to develop AI systems that sense complex environments and approach learning processes in an efficient and generalised manner like we humans do (e.g. embodied AI systems like robots in the real world or agents in videogames adopting intelligent behaviours by taking advantage of vision and language processing).


  • Deep Reinforcement Learning
  • Neural Networks & Deep Learning
  • Embodied AI
  • AI Software Engineering
  • Game AI


  • Junior Data Scientist @ HP Inc
  • AI Teaching Assistant @ UPC School
  • AI Intern Researcher @ UPC
  • Computer Vision Engineer @ Batou xyz
  • Basketball Coach @ Sagrada Familia Claror


Unsupervised Skill Learning from Pixels (BSc Thesis)

Roger Creus Castanyer

This work focuses on the self-acquirement of the fundamental task-agnostic knowledge available within an environment. The aim is to discover and learn baseline representations and behaviours that can later be useful for solving embodied visual navigation downstream tasks.

Unsupervised Skill-Discovery and Skill-Learning in Minecraft

Juan José Nieto, Roger Creus Castanyer, Xavier Giró-i-Nieto

Pre-training Reinforcement Learning agents in a task-agnostic manner has shown promising results. However, previous works still struggle in learning and discovering meaningful skills in high-dimensional state-spaces, such as pixel-spaces. We approach the problem by leveraging unsupervised skill discovery and self-supervised learning of state representations.

Integration of Convolutional Neural Networks in Mobile Applications

Roger Creus Castanyer, Silverio Martínez-Fernández, Xavier Franch


When building Deep Learning (DL) models, data scientists and software engineers manage the trade-off between their accuracy, or any other suitable success criteria, and their complexity. In an environment with high computational power, a common practice is making the models go deeper by designing more sophisticated architectures. However, in the context of mobile devices, which possess less computational power, keeping complexity under control is a must.

PiCoEDL: Discovery and Learning of Minecraft Navigation Goals from Pixels and Coordinates

Juan José Nieto, Roger Creus Castanyer, Xavier Giró-i-Nieto

Defining a reward function in Reinforcement Learning(RL) is not always possible or very costly. For this reason, there is a great interest in training agents in a task-agnostic manner making use of intrinsic motivations and unsupervised techniques. We hypothesize that RL agents will also benefit from unsupervised pre-trainings with no extrinsic rewards, analogously to how humans mostly learn, especially in the early stages of life.

PixelEDL: Unsupervised Skill Discovery and Learning from Pixels

Roger Creus Castanyer, Juan José Nieto, Xavier Giró-i-Nieto

We tackle embodied visual navigation in a task-agnostic set-up by putting the focus on the unsupervised discovery of skills that provide a good coverage of states. Our approach intersects with empowerment: we address the reward-free skill discovery and learning tasks to discover what can be done in an environment and how.

Which Design Decisions in AI-enabled Mobile Applications Contribute to Greener AI?

Roger Creus Castanyer, Silverio Martínez-Fernández, Xavier Franch

The construction, evolution and usage of complex artificial intelligence (AI) models demand expensive computational resources. While currently available high-performance computing environments support well this complexity, the deployment of AI models in mobile devices, which is an increasing trend, is challenging. Our objective is to systematically assess the trade-off between accuracy and complexity when deploying complex AI models (e.g. neural networks) to mobile devices, which have an implicit resource limitation.

Enhancing sequence-to-sequence modelling for RDF triples to natural text

Oriol Domingo, David Bergés, Roser Cantenys, Roger Creus Castanyer, José Adrian Rodríguez Fonollosa

This work establishes key guidelines on how, which and when Machine Translation (MT) techniques are worth applying to RDF-to-Text task. Not only do we apply and compare the most prominent MT architecture, the Transformer, but we also analyze state-of-the-art techniques such as Byte Pair Encoding or Back Translation to demonstrate an improvement in generalization.

MT-adapted datasheets for datasets: Template and repository

Marta Costa-jussà, Roger Creus Castanyer, Oriol Domingo, Albert Domínguez, Miquel Escobar, Cayetana López, Marina Garcia, Margarita Geleta

In this report we are taking the standardized model proposed by Gebru et al. (2018) for documenting the popular machine translation datasets of the EuroParl (Koehn, 2005) and News-Commentary (Barrault et al., 2019). Within this documentation process, we have adapted the original datasheet to the particular case of data consumers within the Machine Translation area. We are also proposing a repository for collecting the adapted datasheets in this research area.