Marco Bagatella
I am a PhD student ETH Zürich and MPI-IS, co-advised by Georg Martius and Andreas Krause. I mostly work on (deep) reinforcement learning, particularly on pre-training and fine-tuning behavior foundation models. I am always happy to talk about research, so feel free to reach out if you want to chat!
⌯⌲ mbagatella at ethz dot ch
selected publications
-
-
TD-JEPA: Latent-predictive Representations for Zero-Shot Reinforcement LearningOral @ International Conference on Learning Representations, 2026 -
Optimistic Task Inference for Behavior Foundation ModelsOral @ International Conference on Learning Representations, 2026 -
DISCOVER: Automated Curricula for Sparse-Reward Reinforcement LearningAdvances in Neural Information Processing Systems, 2025 -
Active Fine-Tuning of Generalist PoliciesInternational Conference on Machine Learning, 2025