docwza/sumolights

SUMO adaptive traffic signal control - DQN, DDPG, Webster's, Max-pressure, Self-Organizing Traffic Lights

sumolights's Issues

Fixed Time Traffic Light parameters

Hello,

I would like to know whether the green_phase/yellow_phase duration in the fixed time traffic light was same as the action repeat duration in the RL based approaches.

Thank you.

How to write such a beautiful code

This is not an issue. First of all, wonderful work. Second, as a Civil student, I use python but just want to know how I can learn to write code well structured like yours (e.g., define folders, define classes). Could you provide some resources for me to learn to code professionally?

After ran python graph_results.py, lack of dqn method figure.

After i ran the steps above, then Visualize results with: python graph_results.py, there are four methods, lack of the dqn method, and the "metrics" folder also lack of dqn folder.

No module named 'tensorflow.initializers'

Hi Wade,

After running the file, it comes this issue, No module named 'tensorflow.initializers',,

Is there some py file missing?

how can i solve this problom

when run this program, the sumo-gui will stop sharply and pycharm will throw the problem in this picture

How to display on the Sumo-gui

Hello, could you tell me how to display on the Sumo-gui.I don't know how to modify these code to realize it.
I'm looking forward to your reply.

node_id == '-13968'

Hi Dr. Genders,

thanks for the great framework!
I could not understand the code "node_id == '-13968'" in networkdata.py. Where does this number come from? Why do you handle it with some extra code?

Best,

after running train_ddpg.sh

learner waiting at barrier ------------
learner proc 0 waiting at offset barrier------------
learner proc 0 broken offset barrier ------------

test

hello,may i ask you a questionn?
i run your program by windows cmd. But, it appears a bug:

Can you look it?
Thank you!
Best Wishes!

Barrier

Hello,
I am reading your code and papers. And I have a question. In your distprocs.py, you define a method and a class. In the function, you first use the Barrier. I have search the Barrier. Are you use the threading or Barrier class?
Best wishes!

ddpg questions

Hello, Wade Genders phd, I have read your paper and run you code. And I have a question. Can you answer it?

I have learned the ddpg algorithm suits the continuous action space. But in the traffic signal control field, the action was define as (0, 1, 2 ,3 means phase selection) or (0, 1 means change phase or keep it).

In your paper, the proposed action space for the adaptive traffic signal controller is the duration of the next green phase in seconds. I guess you define the actor network outputs a decimal and then round it. Right?

So, could teach me the ddpg algorithm actions setting?

test

I am running cmd on a Windows computer,

why does it appers? THANK YOU!!

there are some question when i run this program

thank you for this great project！but i have some issues want to ask you.
when i run this program with by windows pycharm, sumo-gui will be closed automatically and throw these quetion, hao can i solve this problem?

Best wishes.

There is no modification program, but the running result is different from the source program.

Dear Wade, there are some questions about the program.

1. After I ran' pythongraph _ results.py', I found that the error of DQN' distribution of travel times' in box graph was very large (the abnormal value of DQN reached more than 2,000, while SOTL was only about 1,500). I haven't adjusted any parameters. After several training sessions, it's all the same. Excuse me, what is the reason for this?
   

2. In addition, again, no parameters have been modified. After I run' python graph _ results.py', the values of' Queue' are all smaller than the source program (for example, the peak value is only 1500, while the source program exceeds 8000), while the values of' Delay' are consistent with the results of the source program. Excuse me, what is the reason for this?There is no modification program, but the running result is different from the source program.
   

Error: tcpip::Socket::accept() Unable to create listening socket: Address already in use

Hi, I am pleasure to read your paper and interested in your program project. I configure the running environment on Ubuntu18.04 and try to run the experiments. My experiment environment is as follows:
Ubuntu18.04, Anaconda3-5.3.1-Linux-x86_64.sh, python3.7.5, tensorflow1.14.0, matplotlib3.1.1, sumo-1.12.0.
When I run "./train_dqn.sh", there is an error as follow:

I check the traci docs and don not find the connect() function. I add an configuration in .bashrc as "export LIBSUMO_AS_TRACI=1" and "source ~/.bashrc". But this error still exists.
I do not the reason of the problem. Could you help me?

AttributeError: 'Phase' object has no attribute 'state'

start running main...
networks/double.net.xml
SUCCESSFULLY GENERATED NET DATA
 Retrying in 1 seconds
Loading configuration... done.
Traceback (most recent call last):
  File "run.py", line 17, in <module>
    main()
  File "run.py", line 10, in main
    distprocs = DistProcs(args, args.tsc, args.mode)
  File "/home/zlw/PycharmProjects/sumolights/src/distprocs.py", line 71, in __init__
    netdata = sim.update_netdata()
  File "/home/zlw/PycharmProjects/sumolights/src/sumosim.py", line 120, in update_netdata
    tl_junc = self.get_traffic_lights()
  File "/home/zlw/PycharmProjects/sumolights/src/sumosim.py", line 94, in get_traffic_lights
    green_phases = [ p.state for p in logic.getPhases()
  File "/home/zlw/PycharmProjects/sumolights/src/sumosim.py", line 95, in <listcomp>
    if 'y' not in p.state
AttributeError: 'Phase' object has no attribute 'state'
Error: tcpip::Socket::recvAndCheck @ recv: peer shutdown
Quitting (on error).

my sumo version is 1.2.0

Error when running the model

Hello. I followed the instruction to install dependencies. But when I run command
./train_dqn.sh
./train_ddpg.sh

It had an error like this. I do not know how to fix it. Thanks

Sumo: 1.11
traci==1.11
tensorflow==1.14.0
matplotlib==3.1.1

How to import real traffic data

Hello,docwza. I have some real traffic data here. I want to use the rou.xml file of sumo as the vehicle input. Is this feasible. Can I complete my requirements by modifying file vehiclegen

question

hello! I have read your program, but when I read the Neuralagent and RLagent. I did not find them. So, could you tell me the RLagent directory?

Thank you!