Regret Minimisation and System-Efficiency in Route Choice
Traffic congestions present a major challenge in large cities. Consid- ering the distributed, self-interested nature oftraffic we tackle congestions using multiagent reinforcement learning (MARL). In this thesis, we advance the state- of-the-art by delivering the first MARL convergence guarantees in congestion- like problems. We introduce an algorithm through which drivers can learn opti- mal routes by locally estimating the regret associated with their decisions, which we prove to converge to an equilibrium. In order to mitigate the effects ofselfish- ness, we also devise a decentralised tolling scheme, which we prove to minimise traffic congestion levels. Our theoretical results are supported by an extensive empirical evaluation on realistic traffic networks. 1.