Följ
Samuele Tosatto
Samuele Tosatto
Assistant Professor @ Universität Innsbruck
Verifierad e-postadress på uibk.ac.at - Startsida
Titel
Citeras av
Citeras av
År
Learning inverse dynamics models in o (n) time with lstm networks
E Rueckert, M Nakatenus, S Tosatto, J Peters
2017 IEEE-RAS 17th International Conference on Humanoid Robotics (Humanoids …, 2017
832017
Boosted Fitted Q-Iteration
S Tosatto, DE Carlo, P Matteo, R Marcello
International Conference of Machine Learning, 2017
502017
Contextual latent-movements off-policy optimization for robotic manipulation skills
S Tosatto, G Chalvatzaki, J Peters
2021 IEEE international conference on robotics and automation (ICRA), 10815 …, 2021
172021
A Nonparametric Off-Policy Policy Gradient
S Tosatto, J Carvalho, H Abdulsamad, J Peters
International Conference on Artificial Intelligence and Statistics (AISTATS), 2020
142020
Model-free Policy Learning with Reward Gradients
Q Lan, S Tosatto, H Farrahi, A Mahmood
arXiv preprint arXiv:2103.05147, 2021
102021
Dynamic Decision Frequency with Continuous Options
A Karimi, J Jin, J Luo, AR Mahmood, M Jagersand, S Tosatto
2023 IEEE/RSJ International Conference on Intelligent Robots and Systems …, 2023
72023
Exploration Driven By an Optimistic Bellman Equation
S Tosatto, C D'Eramo, J Pajarinen, M Restelli, J Peters
International Joint Conference on Neural Networks, 2019
72019
An alternate policy gradient estimator for softmax policies
S Garg, S Tosatto, Y Pan, M White, AR Mahmood
arXiv preprint arXiv:2112.11622, 2021
62021
Batch reinforcement learning with a nonparametric off-policy policy gradient
S Tosatto, J Carvalho, J Peters
IEEE Transactions on Pattern Analysis and Machine Intelligence 44 (10), 5996 …, 2021
52021
An upper bound of the bias of Nadaraya-Watson kernel regression under Lipschitz assumptions
S Tosatto, R Akrour, J Peters
Stats 4 (1), 1-17, 2020
52020
Deep probabilistic movement primitives with a bayesian aggregator
M Przystupa, F Haghverd, M Jagersand, S Tosatto
2023 IEEE/RSJ International Conference on Intelligent Robots and Systems …, 2023
32023
A temporal-difference approach to policy gradient estimation
S Tosatto, A Patterson, M White, R Mahmood
International Conference on Machine Learning, 21609-21632, 2022
22022
A Gradient Critic for Policy Gradient Estimation
S Tosatto, A Patterson, M White, AR Mahmood
Sixteenth European Workshop on Reinforcement Learning, 2023
12023
Dimensionality Reduction of Movement Primitives in Parameter Space
S Tosatto, J Stadtmüller, J Peters
arXiv preprint arXiv:2003.02634, 2020
12020
Investigating the Benefits of Nonlinear Action Maps in Data-Driven Teleoperation
M Przystupa, G Gidel, ME Taylor, M Jagersand, J Piater, S Tosatto
arXiv preprint arXiv:2410.21406, 2024
2024
Variable-Decision Frequency Option Critic.
A Karimi, J Jin, J Luo, AR Mahmood, M Jägersand, S Tosatto
CoRR, 2022
2022
Off-Policy Reinforcement Learning for Robotics
S Tosatto
Technische Universität Darmstadt, 2021
2021
An Upper Bound of the Bias of Nadaraya-Watson Kernel Regression under Lipschitz Assumptions. Stats 2021, 4, 1–17
S Tosatto, R Akrour, J Peters
s Note: MDPI stays neu-tral with regard to jurisdictional clai-ms in …, 2020
2020
Technical Report:“Exploration Driven by an Optimistic Bellman Equation”
S Tosatto, C D’Eramo, J Pajarinen, M Restelli, J Peters
2018
Revisiting On-Policy Deep Reinforcement Learning
M Kallel, S Tosatto, C D'Eramo
Seventeenth European Workshop on Reinforcement Learning, 0
Systemet kan inte utföra åtgärden just nu. Försök igen senare.
Artiklar 1–20