Hello, I'd like to ask how the reward function in the code is designed, referring to the thesis?

silvery107 / rl-mpc-locomotion

Deep RL for MPC control of Quadruped Robot Locomotion

https://docs.google.com/presentation/d/18bznpYrkCPnhCisySPDz18hvL3Ytere7JiJEbdLvpgU/edit?usp=sharing

MIT License

417 stars 47 forks source link

Hello, I'd like to ask how the reward function in the code is designed, referring to the thesis? #14

Closed chendayuxixi closed 4 months ago

chendayuxixi commented 4 months ago

thank you very much!

silvery107 commented 4 months ago

Hi, thanks for your interests.

The reward design are mainly refered to this paper, and you can also find more details in my slides. Specific rewards are defined in task config files, and computed in this function for each environment.