André Correia 👋

Machine Learning Engineer & Researcher | PhD in Computer Science
Specializing in Demonstration Learning, Reinforcement Learning, and Applied ML Systems

---

👨‍💻 About Me

I am a Machine Learning researcher and engineer with a PhD in Computer Science, focused on demonstration learning and reinforcement learning. My work spans both academic research and industry applications, with publications in peer-reviewed venues and experience deploying ML models in production environments.

I have hands-on experience developing computer vision and machine learning systems, working with large-scale datasets, and evaluating state-of-the-art models across robotics and surveillance domains.

🌐 Portfolio: https://meowatthemoon.github.io/meowatthemoon

---

🔬 Research & Publications

My research focuses on improving the robustness, safety, and scalability of learning from demonstrations and sequence modeling in reinforcement learning.

Selected Publications:

• A Survey of Demonstration Learning
  Comprehensive survey covering learning methods, benchmarks, applications, and open challenges
  📄 https://www.sciencedirect.com/science/article/pii/S0921889024001969

• Hierarchical Decision Transformer
  State-of-the-art hierarchical sequence modeling for offline reinforcement learning
  📄 https://ieeexplore.ieee.org/document/10342230
  💻 https://github.com/meowatthemoon/HDT

• Decision Mamba Architectures
  Transformer-free sequence modeling for offline RL using Mamba architectures
  📄 https://arxiv.org/abs/2405.07943
  💻 https://github.com/meowatthemoon/Decisionmamba

• DEFENDER
  Improving RL safety using small sets of safe and unsafe demonstrations
  📄 https://doi.org/10.14428/esann/2023.ES2023-97
  💻 https://github.com/meowatthemoon/DEFENDER

• Multi-View Contrastive Learning from Demonstrations
  Learning viewpoint-invariant representations for robotic imitation
  📄 https://ieeexplore.ieee.org/document/10023885
  💻 https://github.com/meowatthemoon/CLfD

• Music to Dance as Language Translation
  Translating music into dance motions using Transformer and Mamba models
  📄 https://arxiv.org/abs/2403.15569
  💻 https://github.com/meowatthemoon/MDLT

---

🛠 Technical Skills

• Machine Learning:
  Reinforcement Learning, Imitation Learning, Demonstration Learning, Computer Vision, Supervised Learning

• Frameworks & Tools:
  PyTorch, TensorFlow, NumPy, Pandas, Scikit-Learn, Docker, Git, Linux

• Languages:
  Python, C++, Java

• Deployment & Systems:
  Flask, FastAPI, ROS, ML model deployment in production environments