The publication ‘Approximating Energy Market Clearing and Bidding With Model-Based Reinforcement Learning’ by Thomas Wolgast and Astrid Nieße was successfully published in the interdisciplinary open access journal IEEE Access at the beginning of October. The paper uses multi-agent reinforcement learning to approximate both energy market participants and the energy market itself through learning. The method makes it possible to analyse the effects of energy market rules on resulting market strategies. In the paper we show how the use of domain knowledge and the approximation of the energy market can significantly reduce training time. 

The paper can be found here: https://ieeexplore.ieee.org/document/10703033