Event-Triggered Action-Delayed Reinforcement Learning Control of a Mixed Autonomy Signalised Urban Intersection

We propose an event-triggered framework for deciding the traffic light at each lane in a mixed autonomy scenario. We deploy the decision after a suitable delay, and events are triggered based on the satisfaction of a predefined set of conditions. We design the trigger conditions and the delay to increase the vehicles’ throughput. This way, we achieve full exploitation of autonomous vehicles (AVs) potential. The ultimate goal is to obtain vehicle-flows led by AVs at the head. We formulate the decision process of the traffic intersection controller as a deterministic delayed Markov decision process, i.e., the action implementation and evaluation are delayed. We propose a Reinforcement Learning based model-free algorithm to obtain the optimal policy. We show - by simulations - that our algorithm converges, and significantly reduces the average wait-time and the queues length as the fraction of the AVs increases. Our algorithm outperforms our previous work [1] by a quite significant amount.