Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Andrea Tirinzoni"'
Publikováno v:
Scopus-Elsevier
IJCAI
IJCAI
Many real-world domains are subject to a structured non-stationarity which affects the agent's goals and the environmental dynamics. Meta-reinforcement learning (RL) has been shown successful for training agents that quickly adapt to related tasks. H
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a3177904d406299fc41fffea10a21386
Autor:
Giorgia Ramponi, Marcello Restelli, Matteo Giuliani, Amarildo Likmeta, Andrea Tirinzoni, Alberto Maria Metelli
In real-world applications, inferring the intentions of expert agents (e.g., human operators) can be fundamental to understand how possibly conflicting objectives are managed, helping to interpret the demonstrated behavior. In this paper, we discuss
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::72f9093fee9ae58ed1288c4a4b481f6d
http://hdl.handle.net/11311/1169636
http://hdl.handle.net/11311/1169636
Autor:
Marcello Restelli, Andrea Tirinzoni, Amarildo Likmeta, Alberto Maria Metelli, Riccardo Giol, Danilo Romano
The design of high-level decision-making systems is a topical problem in the field of autonomous driving. In this paper, we combine traditional rule-based strategies and reinforcement learning (RL) with the goal of achieving transparency and robustne
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::680268b8f311a2d86544359dc7610582
http://hdl.handle.net/11585/801953
http://hdl.handle.net/11585/801953
Publikováno v:
IJCNN
Mutual information has been successfully adopted in filter feature-selection methods to assess both the relevancy of a subset of features in predicting the target variable and the redundancy with respect to other variables. However, existing algorith
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::275915e082259b93ed22284d88f76c76
http://arxiv.org/abs/1907.07384
http://arxiv.org/abs/1907.07384
Autor:
JAGADEESAN, MEENA1 mjagadeesan@berkeley.edu, WEI, ALEXANDER1 awei@berkeley.edu, YIXIN WANG1 ywang@eecs.berkeley.edu, JORDAN, MICHAEL I.2 jordan@cs.berkeley.edu, STEINHARDT, JACOB3 jsteinhardt@berkeley.edu
Publikováno v:
Journal of the ACM. Jun2023, Vol. 70 Issue 3, p1-46. 46p.
Autor:
Metelli, Alberto Maria1 (AUTHOR) albertomaria.metelli@polimi.it
Publikováno v:
Intelligenza Artificiale. 2022, Vol. 16 Issue 2, p165-184. 20p.
Publikováno v:
ACM Transactions on Intelligent Systems & Technology; Feb2024, Vol. 15 Issue 1, p1-34, 34p
Publikováno v:
Machine Learning; Sep2021, Vol. 110 Issue 9, p2291-2293, 3p
Autor:
A.M. Metelli
In recent decades, Reinforcement Learning (RL) has emerged as an effective approach to address complex control tasks. In a Markov Decision Process (MDP), the framework typically used, the environment is assumed to be a fixed entity that cannot be alt