search

aqeelanwar / DRLwithTL_real

Python code for Deep Reinforcement Learning with Transfer Learning in aReal Environment using DJI Tello
MIT License
70 stars 18 forks source link

depth #6

Open soldierofhell opened 4 years ago

soldierofhell commented 4 years ago

Hi @aqeelanwar, You are using depth estimation only to simulate reward. Why didn't you decide to use it for choosing action? You could than base reward on change of distance. Regards,

aqeelanwar commented 4 years ago

Hello,

There are plenty of ways the reward function can be shaped. You can use that.