no code implementations • 1 Jan 2024 • Sangjun Bae, Balazs Kulcsar, Sebastien Gros
In the environment, we propose a Q-learning-based PeDP to maximize fast-EVCS' revenue.
no code implementations • 18 Dec 2023 • Sondre Wiersdalen, Mike Pereira, Annika Lang, Gabor Szederkenyi, Jean Auriol, Balazs Kulcsar
Suitable conditions are given on the input function such that the solutions to the model converge to each other at an exponential rate.
no code implementations • 25 May 2022 • Vincent Szolnoky, Viktor Andersson, Balazs Kulcsar, Rebecka Jörnsten
Most complex machine learning and modelling techniques are prone to over-fitting and may subsequently generalise poorly to future data.
1 code implementation • 21 Jan 2022 • Balazs Varga, Balazs Kulcsar, Morteza Haghir Chehreghani
The role of the target network is overtaken by the control input, which also exploits the temporal dependency of samples (opposed to a randomized memory buffer).