search

AndreaVidali / Deep-QLearning-Agent-for-Traffic-Signal-Control

A framework where a deep Q-Learning Reinforcement Learning agent tries to choose the correct traffic light phase at an intersection to maximize traffic efficiency.
MIT License
424 stars 149 forks source link

pelease help me #25

Open QianJin0729 opened 3 years ago

QianJin0729 commented 3 years ago

when I test，but fail. the problem show“The model number specified does not exist in the models folder” can you help me solve it?

greeneley commented 3 years ago

You have not modified yet the configuration in testing_settings.ini By default, testing_main.py will check the model in folder /models/model_2. You can replace the value "2" into another by changing directly the param: model_to_test in testing_settings.ini For example: I trained a model, and it was saved in /models/model_11. To check this model, I must setting like that in testing_setting.ini:

[dir]
models_path_name = models
sumocfg_file_name = sumo_config.sumocfg
model_to_test = 11

Good luck.