DeepMimic
DeepMimic copied to clipboard
xbpeng
Motion imitation with deep reinforcement learning.
Thanks for your code. After I install everything with the correct version, when I do "make", I got the following errors. `22 warnings generated. 22 warnings generated. 25 warnings generated....
hello: I notice that the all configurations in the args file are not include the tasks metioned in the paper. How can I train a new policy with a task...
 @xbpeng Dear Jason, could you please kindly share the traing code of using height map and convolutional layers? Cuz I really want to train the policy to walk in...
The training data we used is 0005_JumpRope001.bvh on http://mocap.cs.sfu.ca/, and the data file is obtained by BvhToDeepMimic conversion, but after a long training, there is still no problem in the...
I find that the characters are slightly different between MCP and DeepMimic, such as action parameters and state. features. What is the difference of environment definitions in these two works?...
Find not work well when I use the theta from the vision-based pose estimators to make a mocap data, is it necessary to perform additional operations on theta besides the...
Hello Jason, I would like to ask is there any specific requirements for the start or end states of demonstration sequence? I am trying to generate motion files based on...
Can I rotate the ground plane some degrees such that the simulated environment is an incline?
A3C: aka Asynchronous Advantage Actor Critic It uses MPI, so I wonder if DeepMimic be trained using A3C?
@mariolew @yjparkLiCS @xbpeng Have you guys implemented ASI? I found the same question after tried my own mocap data, the result is not good in RSI due to the low...