search

DaRL-LibSignal / LibSignal

107 stars 21 forks source link

Regarding the replication results of dqn and colight #17

Open twodog0508 opened 8 months ago

twodog0508 commented 8 months ago

I conducted experiments using dqn and colight methods on a 6x6 network, and the final results were as follows: Dqn: Final Travel Time is 214.5438, mean rewards: -14.1031, queue: 0.4005, delay: 0.0308, throughput: 4652 Total time token: 18397.876304388046 Colight: Final Travel Time is 206.8853, mean rewards: -4.6692, queue: 0.1022, delay: 0.0111, throughput: 4650 Total time token: 16563.93673968315

It seems that there is not much difference in the results between the two methods. Is it my mistake in implementing the method?

derekmei233 commented 8 months ago

Hi, the result is highly dependent on the flow and network configuration. Different algorithms might have little difference if the flow rate is low or has a high bias in some directions. Could you also report some rule-based methods like max pressure as a baseline comparison?