Author

Alberto Maria Metelli

Politecnico di Milano

h-index 15 View on Semantic Scholar

We have 3 of 46 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Oct 2026

Reusing Past Samples in Proximal Policy Optimization: When and How Does It Help?

Among on-policy deep reinforcement learning methods, Proximal Policy Optimization (PPO) has become the de facto standard, due to its consistently strong empirical performance across diverse application domains. However, on-policy methods are inherently sample inefficient: fresh data collected under the current policy i...

Alessandro Montenegro, Riccardo Venturelli, Marco Mussi et al. · 0 citations

Preprint Aug 2026

Why Does Action Chunking Improve Behavioral Cloning Performance in Robotic Control?

In simulated and real-world robotic control settings, it is shown that in simulated and real-world robotic control settings, one can match the performance of action chunking without action chunking---by deploying an action chunking policy as an ensemble of policies with randomized delays.

Filippo Lazzati, Kyle Stachowicz, William Chen et al. · 13 citations · ⚡2

#machine learning Jul 2026

Generalizing Preference-based Reinforcement Learning: a Rationality Model for Incomparability

This work generalizes preference-based RL by formalizing a novel setting in which the expert can also label trajectory pairs as incomparable, i.e., when neither trajectory dominates the other.

Simone Drago, Marco Mussi, L. Bianconi et al. · arXiv.org · 0 citations