Marco Bagatella

PhD student in RL, currently at the Learning and Adaptive Systems group.

prof_pic.jpg

bio

I am a PhD student at MPI-IS and ETH Zürich, co-advised by Georg Martius and Andreas Krause. I am mainly interested in (deep) reinforcement learning. Previosuly, I was fortunate to spend some time at the AIT Lab (ETH Zürich), under the supervision of Prof. Otmar Hilliges, and in the Autonomous Learning Group.

Not so long ago, I obtained a MSc in Computer Science at ETH Zürich, and a few years before that I graduated from Politecnico di Milano (BSc in Engineering of Computing Systems).

research

My current main focus is on (deep) reinforcement learning, and I enjoy researching or learning about any related idea. In particular, my interests include exploration, temporal abstraction and offline approaches. In the long term, I aim to contribute to the understanding of current RL methods, and I am really excited about finding ways to tackle to rich, open-ended environments.

Outside of RL, I have some experience in representation learning and causality, and I like keeping an eye open towards other topics in machine learning or robotics.

news

Aug 01, 2024 🎉 Directed Exploration in Reinforcement Learning from Linear Temporal Logic was accepted at EWRL 2024
Jul 22, 2024 🪧 Two papers I was involved in were presented at ICML 2024
Sep 22, 2023 🎉 Goal-conditioned Offline Planning from Curious Exploration was accepted to NeurIPS 2023
May 31, 2023 🪧 Efficient Learning of High Level Plans from Play was presented at ICRA 2023
Aug 19, 2022 🪧 SFP (previously called TempoRL) was published in TMLR

selected publications

  1. Active Fine-Tuning of Generalist Policies
    Marco Bagatella, Jonas Hübotter, Georg Martius, and 1 more author
    In arXiv 2410.05026, 2024
  2. Zero-shot Offline Imitation Learning via Optimal Transport
    Thomas Rupf, Marco Bagatella, Nico Gürtler Jonas Frey, and 1 more author
    In arXiv 2410.08751, 2024
  3. Causal Action Influence Aware Counterfactual Data Augmentation
    Núria Armengol Urpí, Marco Bagatella, Marin Vlastelica, and 1 more author
    In Forty-first International Conference on Machine Learning, 2024
  4. Goal-conditioned Offline Planning from Curious Exploration
    Marco Bagatella, and Georg Martius
    In Advances in Neural Information Processing Systems, 2023