search

michigan-traffic-lab / Dense-Deep-Reinforcement-Learning

This repo contains the code for paper "Dense reinforcement learning for safety validation of autonomous vehicles"
Other
316 stars 49 forks source link

No module of RLlib.agents when running d2rl_train.py #4

Open hugeshark7 opened 12 months ago

hugeshark7 commented 12 months ago

Hi Haowei, when i follow the instruction runing the D2RL_train.py, it shows no module of RLlib.agents. I do see the initial file, but i have no idea how to register an agent. By the way, can I modify the maps file to train other agents using this D2RL_train.py. I would really appreciate your reply!

miracelplus commented 11 months ago

Could you provide the detailed information about the error? This could come from mismatch rllib versions or other reasons.

hugeshark7 commented 11 months ago

Could you provide the detailed information about the error? This could come from mismatch rllib versions or other reasons.

here are the errors: 2023-10-19 09-57-18 的屏幕截图 @miracelplus thank you again!

miracelplus commented 11 months ago

Could you check the version of ray[rllib] in your local Python environment? Please notice that you will need to install requirements for D2RL training using requirements_d2rl_train.txt.