… traditional fixed timing signal control, the eco-driving strategy in such a situation is needed.
… , the machine learning community takes tree-based models as one kind of the interpretable …

… in traffic signal control, this work proposes learning … these policies are often hard to interpret.
Recent attempts have also been made to develop interpretable traffic signal control policies […

… concerning road regions, traffic signals, and traffic rules, such as speed limits or stop signs,
… for automated vehicles to build an interpretable learning system with high online computing …

… While some work considers to learn an interpretable policy before applying to the real
world [6] or to build a more realistic simulator [61; 75; 76] for direct transferring, there is still a …

… [4] proposed three DQN-based algorithms to obtain an interpretable policy. A simple … with
an uninterpretable approximator. The IntelliLight algorithm was proposed in [34]. The state …

… policies are lack of interpretability. When an end-to-end policy is learned directly from raw
observations to control … with complex decision making such as traffic light passing. Kendall et al…

… , we formulate the policy learning in a road network as a meta-learning problem, where traffic
signal control at each intersection corresponds to a task, and a policy is learned to adapt to …

… on controlling the timing of traffic signal agents, although this control can be integrated with
the control … on a policy π that is intended to be optimized during the learning process towards …

… In such contexts, a learned policy needs for instance to be interpretable, so that it can be …
higher interpretability in reinforcement learning (RL). To that aim, we distinguish interpretability (…

… Learning an interpretable traffic signal control policy. In Proceedings of the 19th International
Conference on Autonomous Agents and MultiAgent Systems (AAMAS 2020). International …