xbpeng / DeepMimic

Motion imitation with deep reinforcement learning.
https://xbpeng.github.io/projects/DeepMimic/index.html
MIT License
2.27k stars 485 forks source link

How to train the baseball pitch policy #61

Open Chootana opened 5 years ago

Chootana commented 5 years ago

Hello,

I want to know how to make the baseball pitching motion like Fig. 7 in your paper.

I knew that the rewards for imitation objects and tasks (eg. target heading, strike) were needed, and I found the script about imitation objective (DeepMimicCore/scenes/SceneImitate.cpp).

I wonder that the script about task objective is also in the same directory, but so far I can't find a specific script about task objective.

I would appreciate it if you could help me.

Thanks,

xbpeng commented 5 years ago

Sorry we have only released the code for imitation. But feel free to ask if you have any questions about the task objectives.

Chootana commented 5 years ago

Thank you for your kindly reply! I'm going to introduce the task objectives.