Deep reinforcement learning is an AI technique for choosing how to act in different situations repeatedly occurring over time. It has shown tremendous success in playing games, such as ATARI video games, chess, Go, and StarCraft, going as far as beating professional human players. While games present certain interesting scientific …
Every study about the energy transition stresses the importance of the role of flexible demand of electricity: when electricity comes from sun or wind, it needs to be used at those moments when it is available (as electricity is difficult to store for later use). A second use of the …
When flexible electrical loads share remaining network capacity, the exact capacity available is usually not known in advance. Furthermore, there may be periods where there is no communication possible. Last week Frits de Nijs (as first author) submitted the final (camera-ready) version of a paper with Matthijs Spaan and me …
When organizations are putting significant effort in innovations and pilot projects and as scientists we have our doubts about the theoretical foundations of the new approach, I strongly believe it is our obligation to warn those organizations. Of course this is particularly the case if these are governmental organizations that …
Last week I started at the Dutch Railways in Bob Huisman’s group on Maintenance Research and Development as a scientific advisor, for one day a week. My aim is to support and further increase the exchange of knowledge and experience between Dutch Railways and Delft University of Technology. I aim …
State-of-the-art in-car navigation systems contribute to preventing road congestion, because avoiding traffic jams helps dissolving it. Currently, the more advanced systems already are using both historic travel times as well as recently observed travel times to estimate future travel times for road segments, and base their route navigation advice upon …