Mirco Mutti

From Parameters to Behaviors: Unsupervised Compression of the Policy Space

Probing in the Dark: State Entropy Maximization for POMDPs

Blindfolded Experts Generalize Better: Insights from Robotic Manipulation and Videogames

State Entropy Regularization for Robust Reinforcement Learning

Towards Principled Unsupervised Multi-Agent Reinforcement Learning

A Theoretical Framework for Partially-Observed Reward States in RLHF

Enhancing Diversity In Parallel Agents: A Maximum State Entropy Exploration Story

A Classification View on Meta Learning Bandits