1 code implementation • 13 May 2024 • André Correia, Luís A. Alexandre
In this work, we introduce two novel methods, Decision Mamba (DM) and Hierarchical Decision Mamba (HDM), aimed at enhancing the performance of the Transformer models.
1 code implementation • 22 Mar 2024 • André Correia, Luís A. Alexandre
We train our method on AIST++ and PhantomDance data sets to teach a robotic arm to dance, but our method can be applied to a full humanoid robot.
no code implementations • 8 May 2023 • André Correia, Luís Alexandre
We propose a task-agnostic method that leverages small sets of safe and unsafe demonstrations to improve the safety of RL agents during learning.
no code implementations • 20 Mar 2023 • André Correia, Luís A. Alexandre
This paper provides a survey of demonstration learning, where we formally introduce the demonstration problem along with its main challenges and provide a comprehensive overview of the process of learning from demonstrations from the creation of the demonstration data set, to learning methods from demonstrations, and optimization by combining demonstration learning with different machine learning methods.
no code implementations • 21 Sep 2022 • André Correia, Luís A. Alexandre
Our method outperforms the baselines in eight out of ten tasks of varied horizons and reward frequencies without prior task knowledge, showing the advantages of the hierarchical model approach for learning from demonstrations using a sequence model.
no code implementations • 30 Jan 2022 • André Correia, Luís A. Alexandre
This paper presents a framework for learning visual representations from unlabeled video demonstrations captured from multiple viewpoints.