Jacklinkk / Graph_CAVs

The source code for our paper: Graph Reinforcement Learning Application to Co-operative Decision-Making in Mixed Autonomy Traffic: Framework, Survey, and Challenges. This code is developed based on our previous repository TorchGRL.
58 stars 7 forks source link

How to prevent nan values in Loss and Average_Q value during training #10

Open waleedrafique51 opened 2 months ago

waleedrafique51 commented 2 months ago

Thanks author for sharing your work..Could you guide me How to prevent nan values in Loss and Average_Q value during training.As I have received nan values while executing discrete Deep Q leaning method