Figures & data
Figure 1. This figure shows an example three-agent DCEE. Each agent controls one variable and the settings of these three variables determine the reward of the two constraints (and thus the total team reward).
![Figure 1. This figure shows an example three-agent DCEE. Each agent controls one variable and the settings of these three variables determine the reward of the two constraints (and thus the total team reward).](/cms/asset/093310ad-54d5-40f3-968b-363404d90c47/ccos_a_885282_f0001_c.jpg)
Figure 3. The signal scheme index for each DCEE agent, and its corresponding (greenoffset, greentime) value, defining an active phase of 60 s. Note that greenoffset and greentime increase at 5-s intervals, a necessary discretisation.
![Figure 3. The signal scheme index for each DCEE agent, and its corresponding (greenoffset, greentime) value, defining an active phase of 60 s. Note that greenoffset and greentime increase at 5-s intervals, a necessary discretisation.](/cms/asset/7c989317-b33c-4c2c-b074-5cb0aa005b37/ccos_a_885282_f0003_b.gif)
Figure 4. The full signal scheme for an intersection, given a specific active phase. Time flows from left to right: the calculated active phase is active for North–South in the first 60 s, before switching to East–West in the next 60 s. The whole signal scheme repeats after 120 s total.
![Figure 4. The full signal scheme for an intersection, given a specific active phase. Time flows from left to right: the calculated active phase is active for North–South in the first 60 s, before switching to East–West in the next 60 s. The whole signal scheme repeats after 120 s total.](/cms/asset/1c5d5ef8-2ac6-40ce-85dd-aa20e17ec267/ccos_a_885282_f0004_c.jpg)
Figure 5. Average delay and throughput for a light traffic level (10 cars spawned per minute at each entrance). Error bars show one standard deviation.
![Figure 5. Average delay and throughput for a light traffic level (10 cars spawned per minute at each entrance). Error bars show one standard deviation.](/cms/asset/93cfe567-03dd-4e7f-a828-a1a5ce2f200c/ccos_a_885282_f0005_c.jpg)
Figure 6. Average delay and throughput for a heavy traffic level (30 cars spawned per minute at each entrance). Error bars show one standard deviation.
![Figure 6. Average delay and throughput for a heavy traffic level (30 cars spawned per minute at each entrance). Error bars show one standard deviation.](/cms/asset/e0e5164f-a901-4829-b075-e20fd8a247e7/ccos_a_885282_f0006_c.jpg)
Figure 7. The reward samples observed during a single run with a heavy traffic level and either delay (a) or throughput (b) as a reward signal. Colour indicates the timing of the sample, with blue early in the run, and red at the end of the run. The objectives (minimising delay on x-axis and maximising throughput on y-axis) are observed to be correlated.
![Figure 7. The reward samples observed during a single run with a heavy traffic level and either delay (a) or throughput (b) as a reward signal. Colour indicates the timing of the sample, with blue early in the run, and red at the end of the run. The objectives (minimising delay on x-axis and maximising throughput on y-axis) are observed to be correlated.](/cms/asset/54c4e1db-5cdf-4b76-b39d-4dc41ac80867/ccos_a_885282_f0007_c.jpg)
Figure 8. Average delay for a light traffic level (10 cars spawned per minute at each entrance). Comparison of two single-objective approaches and linear scalarisation. Error bars show one standard deviation.
![Figure 8. Average delay for a light traffic level (10 cars spawned per minute at each entrance). Comparison of two single-objective approaches and linear scalarisation. Error bars show one standard deviation.](/cms/asset/3f46a821-c8fc-45ba-8871-886552d6cfeb/ccos_a_885282_f0008_c.jpg)
Figure 9. Average delay and throughput for a heavy traffic level (30 cars spawned per minute at each entrance). Comparison of two single-objective approaches and linear scalarisation. Error bars show one standard deviation.
![Figure 9. Average delay and throughput for a heavy traffic level (30 cars spawned per minute at each entrance). Comparison of two single-objective approaches and linear scalarisation. Error bars show one standard deviation.](/cms/asset/ddec9d87-9c85-4e3b-ad11-a7d6f30b5964/ccos_a_885282_f0009_c.jpg)
Figure 10. Average delay for a light traffic level (10 cars spawned per minute at each entrance). Comparison of delay, scalarised (delay and throughput), delay-squared and a different scalarised (delay squared and throughput) reward signal. Error bars show one standard deviation.
![Figure 10. Average delay for a light traffic level (10 cars spawned per minute at each entrance). Comparison of delay, scalarised (delay and throughput), delay-squared and a different scalarised (delay squared and throughput) reward signal. Error bars show one standard deviation.](/cms/asset/befde66b-d07a-4e5d-be46-6c1b6cebba98/ccos_a_885282_f0010_c.jpg)
Figure 11. Average delay and throughput for a heavy traffic level (30 cars spawned per minute at each entrance). Comparison of delay, scalarised (delay and throughput) and delay-squared reward signals. Scalarised with delay-squared and throughput yields the same performance as delay-squared alone. Error bars show one standard deviation.
![Figure 11. Average delay and throughput for a heavy traffic level (30 cars spawned per minute at each entrance). Comparison of delay, scalarised (delay and throughput) and delay-squared reward signals. Scalarised with delay-squared and throughput yields the same performance as delay-squared alone. Error bars show one standard deviation.](/cms/asset/829e6ef9-48b3-4607-8c32-935b6c91b18f/ccos_a_885282_f0011_c.jpg)