Selected Research
I'm interested in multimodal representation learning and reinforcement learning. Here you can find some selective publications. For a complete list check out this link.
|
|
A Super-human Vision-based Reinforcement Learning Agent for Autonomous Racing in Gran Turismo
Miguel Vasco*, Takuma Seno*, Kenta Kawamoto, Kaushik Subramanian, Peter R Wurman, Peter Stone
arXiv, 2024
arxiv /
We contribute the first vision-based super-human car racing agent, able to outperform the best human drivers in time-trial races in Gran Turismo 7.
|
|
Geometric Multimodal Contrastive Representation Learning
Petra Poklukar*, Miguel Vasco*, Hang Yin, Francisco S. Melo, Ana Paiva, Danica Kragic
International Conference on Machine Learning (ICML), 2022
link /
code /
We show how contrastive learning can be used to learn multimodal representations that are robust to missing information at test time. We evaluate our approach in supervised, unsupervised and reinforcement learning tasks.
|
|
How to Sense the World: Leveraging Hierarchy in Multimodal Perception for Robust Reinforcement Learning Agents
Miguel Vasco, Hang Yin, Francisco S Melo, Ana Paiva
International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2022
link /
code /
We introduce MUSE, a multimodal representation learning module for RL agents that allows the robust execution of tasks, regardless of the available modalities at execution.
|
|
Leveraging Hierarchy in Multimodal Generative Models for Effective Cross-modality Inference
Miguel Vasco, Hang Yin, Francisco S. Melo, Ana Paiva
Neural Networks (Special Issue on AI and Brain Science: Brain-inspired AI), 2021
link /
code /
We investigate the problem of cross-modality inference (CMI) in multimodal generative models and show the potential of considering hierarchical representation spaces. We additionally contribute with a novel multimodal benchmark dataset.
|
|
Playing Games in the Dark: An Approach for Cross-modality Transfer in Reinforcement Learning
Rui Silva, Miguel Vasco, Francisco S Melo, Ana Paiva, Manuela Veloso
International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2020
link /
code /
We propose a framework that allows RL agents to transfer policies across different modalities (even to unseen ones during policy training!). We also contribute multimodal Atari environments.
|
Teaching
FDD3359 Reinforcement Learning, PhD, KTH Royal Institute of Technology - Spring 2024
DD2430 Project Course in Data Science, MSc, KTH Royal Institute of Technology - Fall 2023
Planning, Learning and Intelligent Decision-Making, MSc, Instituto Superior Técnico, University of Lisbon - Fall 2022, Fall 2021
Computation and Society (AI Ethics), BSc, Instituto Superior Técnico, University of Lisbon - Spring 2019, Spring 2020
|
Students
Current PhD Students
Alfredo Reichlin, KTH Royal Institute of Technology (co-supervised with Danica Kragic and Hang Yin)
Nona Rajabi, KTH Royal Institute of Technology (co-supervised with Danica Kragic and Mårten Björkman)
Farzaneh Taleb, KTH Royal Institute of Technology (co-supervised with Danica Kragic and Mårten Björkman)
Bernardo Esteves, Instituto Superior Técnico, University of Lisbon (co-supervised with Francisco S. Melo)
Former Students
Afonso Fernandes, Instituto Superior Técnico, University of Lisbon (co-supervised with Francisco S. Melo), Master Thesis, 2023
Bernardo Esteves, Instituto Superior Técnico, University of Lisbon (co-supervised with Francisco S. Melo), Master Thesis, 2023
Fábio Vital, Instituto Superior Técnico, University of Lisbon (co-supervised with Alberto Sardinha and Francisco S. Melo), Master Thesis, 2022
|
|