stefanwanckel

Are your surfaces really reflective? is your light source focal?

I also did that myself. glad that I could be of some help :) Yes, the training takes very long when doing position control. Unfortunately Pybullet doesnt support multithreading atm...

In general, I was not able to train any models for the past 2 months. I have tried several, but I almost always get similar results: Either the arm "folds"...

When moving with position control the joint values that one gets by calling getjointState can slightly vary from the values that we put into the position control function. This error...

One more thought: I believe that your threshold for sparse rewards is too small. Especially if you train wihtout HER the model might not see enought reward signals. I chose...

Another thought: when training her, the reward for sampled goals is calculated using the "compute_reward" function defined in the environment. Because I did not specify the axis along which to...

*Addendum: Even with only ddpg, the robot arm moves into said position and it is very difficult for him to change its position from there. I also implemented ddpg from...

By folding I mean that the robot goes into a configuration where all joint angles are at max or at min and it cant get out of that configuration. Here...