Simplifying the example code and interacting with the NN
here is the pared down ant.py that i’ll be using moving forward. notice that it doesn’t have any observations. there’s a minimum of 1 observation so i set it to 1
ant.py
1
notes from playing around with isaac gym’s ant example
for cartpole i’d often run the trained policy with just 1 env to print the rewards and see how they changed per behavior. but these…
this post is based on the official installation guides for CUDA and Isaac Gym and many hours of debugging. the whole process takes me about 50 minutes from reinstalling linux to running joint_monkey.py
joint_monkey.py