stanfordsnr/indigo

Empirically learned congestion control by imitation learning with RNNs

Indigo: Empirically learned congestion control

indigo's Issues

How to solve those problems?

Hello,Hello, I ran into some problems while running this project. I will follow the steps below:
git clone https://github.com/StanfordSNR/pantheon.git
git submodule update --init --recursive # or tools/fetch_submodules.sh
src/experiments/setup.py --install-deps --all
src/experiments/setup.py --setup --all
src/experiments/test.py local --schmes "indigo"
Then I download the file under ‘indigo’ folder and copy it to ‘indigo’, but I have the following problems and how to solve it？
File "src/experiments/test.py", line 808, in main
run_tests(args)
File "src/experiments/test.py", line 749, in run_tests
getattr(args, 'remote_path', None))
File "/home/zouyong/pantheon/src/experiments/helpers/utils.py", line 180, in get_git_summary
local_git_summary = check_output(git_summary_src, cwd=context.base_dir)
File "/home/zouyong/pantheon/src/experiments/helpers/subprocess_wrappers.py", line 29, in check_output
return subprocess.check_output(cmd, **kwargs)
File "/usr/lib/python2.7/subprocess.py", line 216, in check_output
process = Popen(stdout=PIPE, *popenargs, **kwargs)
File "/usr/lib/python2.7/subprocess.py", line 394, in init
errread, errwrite)
File "/usr/lib/python2.7/subprocess.py", line 1047, in _execute_child
raise child_exception
OSError: [Errno 2] No such file or directory
Thank you for your answer

Questions about the dagger/best_cwnds.yml

Hi:

Sorry to bother you~ I have some questions about how to generate the expert data. I noticed there are some predefined "best_cwnd_map" data in dagger/best_cwnds.yml, but I have no idea how to generate it.

I'd really appreciate it if you could help me with my questions～