Mirco Mutti
Mirco Mutti
E-mail confirmado em polimi.it
Título
Citado por
Citado por
Ano
Configurable Markov Decision Processes
AM Metelli, M Mutti, M Restelli
Proceedings of the 35th International Conference on Machine Learning, 2018
292018
Task-Agnostic Exploration via Policy Gradient of a Non-Parametric State Entropy Estimate
M Mutti, L Pratissoli, M Restelli
Proceedings of the AAAI Conference on Artificial Intelligence 35 (10), 9028-9036, 2021
13*2021
An Intrinsically-Motivated Approach for Learning Highly Exploring and Fast Mixing Policies
M Mutti, M Restelli
Proceedings of the AAAI Conference on Artificial Intelligence 34 (04), 5232-5239, 2019
82019
Learning to Explore a Class of Multiple Reward-Free Environments
M Mutti, M Mancassola, M Restelli
Self-Supervision for Reinforcement Learning Workshop, 2021
12021
Unsupervised Reinforcement Learning in Multiple Environments
M Mutti, M Mancassola, M Restelli
arXiv preprint arXiv:2112.08746, 2021
2021
The Importance of Non-Markovianity in Maximum State Entropy Exploration
M Mutti, R De Santi, M Restelli
ICML 2021 Workshop on Unsupervised Reinforcement Learning, 2021
2021
Reward-Free Policy Space Compression for Reinforcement Learning
M Mutti, S Del Col, M Restelli
ICML 2021 Workshop on Unsupervised Reinforcement Learning, 2021
2021
Learning to Explore Multiple Environments without Rewards
M Mutti, M Mancassola, M Restelli
ICML 2021 Workshop on Unsupervised Reinforcement Learning, 2021
2021
Configurable Markov Decision Processes
M MUTTI
Italy, 2018
2018
O sistema não pode executar a operação agora. Tente novamente mais tarde.
Artigos 1–9