Pietro Mazzaglia's Projects
[ICLR 2023] Choreographer: a model-based agent that discovers and learns unsupervised skills in latent imagination, and it's able to efficiently coordinate and adapt the skills to solve downstream tasks.
[NeurIPS 2021] Contrastive learning formulation of the active inference framework, for matching visual goal states.
[GenRL] Multimodal foundation world models allow grounding language and video prompts into embodied domains, by turning them into sequences of latent world model states. Latent state sequences can be decoded using the decoder of the model, allowing visualization of the expected behavior, before training the agent to execute it.
[AAAI-22] Curiosity-based objective for exploration with reinforcement learning in state-based and vision-based environments.
[ICML 2023] Pre-train world model-based agents with different unsupervised strategies, fine-tune the agent's components selectively, and use planning (Dyna-MPC) during fine-tuning.
Personal GitHub page.
ProMP: Proximal Meta-Policy Search
[RA-L 2024] Novel action spaces leveraging redundancy in 7 DoF arms enable efficient & precise learning in robotic manipulation
Front-End Interface for a universitarian Start Up project
Projects of the Udacity Scholarship offered by Google.
PyTorch implementation of the VIME paper (Variational Information Maximizing Exploration)
A Vue component to render graphs on canvas, based on Vis.js