Task-Agnostic Exploration via Policy Gradient of a Non-Parametric State Entropy Estimate M Mutti, L Pratissoli, M Restelli AAAI 2021, 2021 | 60* | 2021 |
Configurable Markov Decision Processes AM Metelli, M Mutti, M Restelli ICML 2018, 2018 | 47 | 2018 |
An Intrinsically-Motivated Approach for Learning Highly Exploring and Fast Mixing Policies M Mutti, M Restelli AAAI 2020, 2019 | 24 | 2019 |
Unsupervised Reinforcement Learning in Multiple Environments M Mutti, M Mancassola, M Restelli AAAI 2022, 2022 | 23 | 2022 |
The Importance of Non-Markovianity in Maximum State Entropy Exploration M Mutti, R De Santi, M Restelli ICML 2022, 2022 | 21 | 2022 |
Challenging Common Assumptions in Convex Reinforcement Learning M Mutti, R De Santi, P De Bartolomeis, M Restelli NeurIPS 2022, 2022 | 17 | 2022 |
Provably Efficient Causal Model-Based Reinforcement Learning for Systematic Generalization M Mutti, R De Santi, E Rossi, JF Calderon, M Bronstein, M Restelli AAAI 2023, 2022 | 14* | 2022 |
Convex Reinforcement Learning in Finite Trials M Mutti, R De Santi, P De Bartolomeis, M Restelli JMLR 24 (250), 1-42, 2023 | 10 | 2023 |
Persuading Farsighted Receivers in MDPs: the Power of Honesty M Bernasconi, M Castiglioni, A Marchesi, M Mutti NeurIPS 2023, 2023 | 4 | 2023 |
Reward-Free Policy Space Compression for Reinforcement Learning M Mutti, S Del Col, M Restelli AISTATS 2022, 2022 | 4 | 2022 |
Unsupervised Reinforcement Learning via State Entropy Maximization M Mutti PhD Thesis, Università di Bologna, 2023 | 3 | 2023 |
A Tale of Sampling and Estimation in Discounted Reinforcement Learning AM Metelli, M Mutti, M Restelli AISTATS 2023, 2023 | 2 | 2023 |
How to Explore with Belief: State Entropy Maximization in POMDPs R Zamboni, D Cirino, M Restelli, M Mutti ICML 2024, 2024 | 1 | 2024 |
Offline Inverse RL: New Solution Concepts and Provably Efficient Algorithms F Lazzati, M Mutti, AM Metelli ICML 2024, 2024 | 1 | 2024 |
A Framework for Partially Observed Reward-States in RLHF C Kausik, M Mutti, A Pacchiano, A Tewari arXiv preprint arXiv:2402.03282, 2024 | 1 | 2024 |
Non-Markovian Policies for Unsupervised Reinforcement Learning in Multiple Environments P Maldini, M Mutti, R De Santi, M Restelli First Workshop on Pre-training: Perspectives, Pitfalls, and Paths Forward at …, 2022 | 1 | 2022 |
The Limits of Pure Exploration in POMDPs: When the Observation Entropy is Enough R Zamboni, D Cirino, M Restelli, M Mutti arXiv preprint arXiv:2406.12795, 2024 | | 2024 |
How to Scale Inverse RL to Large State Spaces? A Provably Efficient Approach F Lazzati, M Mutti, AM Metelli arXiv preprint arXiv:2406.03812, 2024 | | 2024 |
Test-Time Regret Minimization in Meta Reinforcement Learning M Mutti, A Tamar ICML 2024, 2024 | | 2024 |
Geometric Active Exploration in Markov Decision Processes: the Benefit of Abstraction R De Santi, FA Joseph, N Liniger, M Mutti, A Krause ICML 2024, 2024 | | 2024 |