D'ERAMO, CARLO
D'ERAMO, CARLO
DIPARTIMENTO DI ELETTRONICA, INFORMAZIONE E BIOINGEGNERIA
Boosted Fitted Q-Iteration
2017-01-01 Tosatto, Samuele; Pirotta, M.; D'Eramo, C.; Restelli, M.
Estimating Maximum Expected Value through Gaussian Approximation
2016-01-01 D'Eramo, Carlo; Restelli, Marcello; Nuara, Alessandro
Estimating the maximum expected value in continuous reinforcement learning problems
2017-01-01 D'Eramo, Carlo; Nuara, Alessandro; Pirotta, Matteo; Restelli, Marcello
Exploiting Action-Value Uncertainty to Drive Exploration in Reinforcement Learning
2019-01-01 D'Eramo, Carlo; Cini, Andrea; Restelli, Marcello
Exploiting structure and uncertainty of Bellman updates in Markov decision processes
2017-01-01 Tateo, Davide; D'Eramo, Carlo; Nuara, Alessandro; Restelli, Marcello; Bonarini, Andrea
Exploration Driven by an Optimistic Bellman Equation
2019-01-01 Tosatto, Samuele; D'Eramo, Carlo; Pajarinen, Joni; Restelli, Marcello; Peters, Jan
Gaussian approximation for bias reduction in Q-learning
2021-01-01 D'Eramo, C.; Cini, A.; Nuara, A.; Pirotta, M.; Alippi, C.; Peters, J.; Restelli, M.
MushroomRL: Simplifying Reinforcement Learning Research
2021-01-01 D'Eramo, C; Tateo, D; Bonarini, A; Restelli, M; Peters, J
Sharing Knowledge in Multi-Task Deep Reinforcement Learning
2020-01-01 D'Eramo, C.; Tateo, D.; Bonarini, A.; Restelli, M.; Peters, J.