Mirco Mutti

Publication Activity (10 Years)

Years Active: 2018-2024
Publications (10 Years): 30

Top Topics

Regret Minimization

Markov Decision Process

Eligibility Traces

Reinforcement Learning

Top Venues

Publications

Chinmaya Kausik, Mirco Mutti, Aldo Pacchiano, Ambuj Tewari
A Framework for Partially Observed Reward-States in RLHF. CoRR (2024)
Riccardo De Santi, Federico Arangath Joseph, Noah Liniger, Mirco Mutti, Andreas Krause
Geometric Active Exploration in Markov Decision Processes: the Benefit of Abstraction. CoRR (2024)
Riccardo Zamboni, Duilio Cirino, Marcello Restelli, Mirco Mutti
How to Explore with Belief: State Entropy Maximization in POMDPs. CoRR (2024)
Filippo Lazzati, Mirco Mutti, Alberto Maria Metelli
How to Scale Inverse RL to Large State Spaces? A Provably Efficient Approach. CoRR (2024)
Mirco Mutti, Riccardo De Santi, Marcello Restelli, Alexander Marx, Giorgia Ramponi
Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning. ICLR (2024)
Riccardo Zamboni, Duilio Cirino, Marcello Restelli, Mirco Mutti
The Limits of Pure Exploration in POMDPs: When the Observation Entropy is Enough. CoRR (2024)
Mirco Mutti, Aviv Tamar
Test-Time Regret Minimization in Meta Reinforcement Learning. CoRR (2024)
Filippo Lazzati, Mirco Mutti, Alberto Maria Metelli
Offline Inverse RL: New Solution Concepts and Provably Efficient Algorithms. CoRR (2024)
Mirco Mutti, Riccardo De Santi, Marcello Restelli, Alexander Marx, Giorgia Ramponi
Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning. CoRR (2023)
Mirco Mutti, Riccardo De Santi, Emanuele Rossi, Juan Felipe Calderón, Michael M. Bronstein, Marcello Restelli
Provably Efficient Causal Model-Based Reinforcement Learning for Systematic Generalization. AAAI (2023)
Alberto Maria Metelli, Mirco Mutti, Marcello Restelli
A Tale of Sampling and Estimation in Discounted Reinforcement Learning. CoRR (2023)
Martino Bernasconi, Matteo Castiglioni, Alberto Marchesi, Mirco Mutti
Persuading Farsighted Receivers in MDPs: the Power of Honesty. CoRR (2023)
Alberto Maria Metelli, Mirco Mutti, Marcello Restelli
A Tale of Sampling and Estimation in Discounted Reinforcement Learning. AISTATS (2023)
Martino Bernasconi, Matteo Castiglioni, Alberto Marchesi, Mirco Mutti
Persuading Farsighted Receivers in MDPs: the Power of Honesty. NeurIPS (2023)
Mirco Mutti, Riccardo De Santi, Piersilvio De Bartolomeis, Marcello Restelli
Convex Reinforcement Learning in Finite Trials. J. Mach. Learn. Res. 24 (2023)
Mirco Mutti, Riccardo De Santi, Piersilvio De Bartolomeis, Marcello Restelli
Challenging Common Assumptions in Convex Reinforcement Learning. CoRR (2022)
Mirco Mutti, Mattia Mancassola, Marcello Restelli
Unsupervised Reinforcement Learning in Multiple Environments. AAAI (2022)
Mirco Mutti, Stefano Del Col, Marcello Restelli
Reward-Free Policy Space Compression for Reinforcement Learning. CoRR (2022)
Mirco Mutti, Riccardo De Santi, Emanuele Rossi, Juan Felipe Calderón, Michael Bronstein, Marcello Restelli
Provably Efficient Causal Model-Based Reinforcement Learning for Systematic Generalization. CoRR (2022)
Mirco Mutti, Stefano Del Col, Marcello Restelli
Reward-Free Policy Space Compression for Reinforcement Learning. AISTATS (2022)
Mirco Mutti, Riccardo De Santi, Marcello Restelli
The Importance of Non-Markovianity in Maximum State Entropy Exploration. CoRR (2022)
Mirco Mutti, Riccardo De Santi, Piersilvio De Bartolomeis, Marcello Restelli
Challenging Common Assumptions in Convex Reinforcement Learning. NeurIPS (2022)
Mirco Mutti, Riccardo De Santi, Marcello Restelli
The Importance of Non-Markovianity in Maximum State Entropy Exploration. ICML (2022)
Mirco Mutti, Mattia Mancassola, Marcello Restelli
Unsupervised Reinforcement Learning in Multiple Environments. CoRR (2021)
Mirco Mutti, Lorenzo Pratissoli, Marcello Restelli
Task-Agnostic Exploration via Policy Gradient of a Non-Parametric State Entropy Estimate. AAAI (2021)
Mirco Mutti, Lorenzo Pratissoli, Marcello Restelli
A Policy Gradient Method for Task-Agnostic Exploration. CoRR (2020)
Mirco Mutti, Marcello Restelli
An Intrinsically-Motivated Approach for Learning Highly Exploring and Fast Mixing Policies. AAAI (2020)
Mirco Mutti, Marcello Restelli
An Intrinsically-Motivated Approach for Learning Highly Exploring and Fast Mixing Policies. CoRR (2019)
Alberto Maria Metelli, Mirco Mutti, Marcello Restelli
Configurable Markov Decision Processes. CoRR (2018)
Alberto Maria Metelli, Mirco Mutti, Marcello Restelli
Configurable Markov Decision Processes. ICML (2018)