@mastersthesis {xCreus, title = {Unsupervised skill learning from pixels}, year = {2021}, abstract = {

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. Specifically, the presented approach extends the idea of the "Explore, Discover and Learn" (EDL) paradigm to the pixel domain. This way, this work is centered in the representations and behaviours that can be learnt by an agent that only integrates an image capture sensor. Both the agents and the environment that is used in this work run over the Habitat AI simulator, which is developed by Facebook AI, and renders 3D fotorealistic views of the insides of apartments.





}, author = {Creus, Roger}, editor = {Nieto, Juan Jos{\'e} and Xavier Gir{\'o}-i-Nieto} } @conference {cNietoa, title = {Unsupervised Skill-Discovery and Skill-Learning in Minecraft}, booktitle = {ICML 2021 Workshop on Unsupervised Reinforcement Learning (URL)}, year = {2021}, month = {07/2021}, abstract = {

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. In our work, we learn a compact latent representation by making use of variational and contrastive techniques. We demonstrate that both enable RL agents to learn a set of basic navigation skills by maximizing an information theoretic objective. We assess our method in Minecraft 3D pixel maps with different complexities. Our results show that representations and conditioned policies learned from pixels are enough for toy examples, but do not scale to realistic and complex maps. To overcome these limitations, we explore alternative input observations such as the relative position of the agent along with the raw pixels.

}, author = {Nieto, Juan Jos{\'e} and Creus, Roger and Xavier Gir{\'o}-i-Nieto} }