IEL @ BuildSys22

Last updated on Dec 5, 2022 1 min read

⁉️How can we use past data to generate synthetic data to improve our learning controllers 🤨? 

‼️Check our our paper led by Marta Fochesato (ETH Zürich) and Fazel Khayatian (Empa) at ACM BuildSys'22 tomorrow (Nov 10).

Marta implements a TimeGAN approach in CityLearn and demonstrates the improvement of the control performance.

👉 On the use of conditional TimeGAN to enhance the robustness of a reinforcement learning agent in the building domain

Zoltan Nagy
Zoltan Nagy
Assistant Professor

My research interests include reinforcement learning for buildings and smart cities.