Carlo D'Eramo
Carlo D'Eramo
Postdoctoral researcher @ Technische Universitšt Darmstadt
Verified email at robot-learning.de - Homepage
TitleCited byYear
Estimating the Maximum Expected Value through Gaussian Approximation
C D’Eramo, A Nuara, M Restelli
Proceedings of The 33rd International Conference on Machine Learning, 1032-1040, 2016
192016
Boosted Fitted Q-Iteration
S Tosatto, M Pirotta, C D'Eramo, M Restelli
Proceedings of The 34th International Conference on Machine Learning, 3434-3443, 2017
112017
Estimating the Maximum Expected Value in Continuous Reinforcement Learning Problems
C D'Eramo, A Nuara, M Pirotta, R Marcello
AAAI Conference on Artificial Intelligence, 1840-1846, 2017
62017
Generalized Mean Estimation in Monte-Carlo Tree Search
T Dam, P Klink, C D'Eramo, J Peters, J Pajarinen
arXiv preprint arXiv:1911.00384, 2019
2019
Exploration Driven by an Optimistic Bellman Equation
S Tosatto, C D’Eramo, J Pajarinen, M Restelli, J Peters
2019 International Joint Conference on Neural Networks (IJCNN), 1-8, 2019
2019
Exploiting Action-Value Uncertainty to Drive Exploration in Reinforcement Learning
C D’Eramo, A Cini, M Restelli
2019 International Joint Conference on Neural Networks (IJCNN), 1-8, 2019
2019
On the exploitation of uncertainty to improve Bellman updates and exploration in Reinforcement Learning
C D'ERAMO
Italy, 2019
2019
Exploiting structure and uncertainty of Bellman updates in Markov decision processes
D Tateo, C D'Eramo, A Nuara, M Restelli, A Bonarini
Symposium on Adaptive Dynamic Programming and Reinforcement Learning (IEEE†…, 2017
2017
On the use of deep Boltzmann machines for road signs classification
C D'ERAMO
Italy, 2015
2015
The system can't perform the operation now. Try again later.
Articles 1–9