Page 134 - Read Online
P. 134

Boin et al. Intell Robot 2022;2(2):145­67  I http://dx.doi.org/10.20517/ir.2022.11  Page 159



























































                                  (a) Platoon 1                            (b) Platoon 2

               Figure 7. Results for a specific 60s test episode using the 2 vehicle 2 platoon environment trained using Inter-FRL with weight aggregation.


               3.3.1. Performance across 4 random seeds
               The performance for the platoon is calculated by averaging the cumulative reward generated by the simulation
               foreachofthe4randomseedsandissummarizedinTable5. TheresultsinTable5summarizetheperformance
               forno-FRL,Intra-FRLGA,andlastlyIntra-FRLWA.ItisobservedthatIntra-FRLWAperformsmostfavourably,
               followed by no-FRL and lastly Intra-FRLGA.
   129   130   131   132   133   134   135   136   137   138   139