search

pipatth / robot-rl-cscie89

19 stars 13 forks source link

Great job! I am a noob. Do you get any idea to train fetchpickandplace-v1 using the same algorithm? #1

Closed Chao-Hou closed 4 years ago

Chao-Hou commented 6 years ago

Great job! I am a noob. Do you get any idea to train fetchpickandplace-v1 using the same algorithm? some thing i really need to pay attention , and the difference between the two tasks. I tried to train it on the basis of your code. but didn't make it. Thanks in advance!

pipatth commented 6 years ago

Hi. I've never tried fetchpickandplace-v1. Pick and place seems to have more observation spaces and action spaces. You might have to tweak the code. If the code is working but it doesn't converge, I would say that you might want to try different neural net architectures (e.g. more layers, convolutional, etc.). Let me know if you have further questions. Good luck!

Chao-Hou commented 6 years ago

I tried several time, but still couldn't make it . Would you like to try fetchpickandplace-v1 with the same algorithm? Considering you have done fetchreach so perfect, it cannot be difficult for you.

pipatth commented 6 years ago

Hi Chao-Hou. I don't have a plan to do fetchpickandplace-v1 at this point. But I'll be glad to help anyone. Thanks.

GbengaOdesanmi commented 5 years ago

Hi pipatth, Thanks for your awesome presentation, I would be glad if you can help me because am finding it difficult to understand some basic implementation process. Thanks in anticipation my email(gbenga28@gmail.com)

chaiban commented 5 years ago

Hi @pipatth , did you manage to implement for PickAndPlace ?, if so can you share the code ? Thank you! mail: bandi.chai414@gmail.com

pipatth commented 5 years ago

@chaiban I haven't try PickAndPlace. It shouldn't be much different than Fetch. You need to give the learner some rewards along the way (hindsight experience replay). Otherwise, the learning is so slow.

pipatth commented 5 years ago

@chaiban I haven't tried customer environment on Mujoco before. Have you tried looking at https://github.com/openai/gym/tree/master/gym/envs/mujoco ?

chaiban commented 5 years ago

@pipatth Yes, I saw the environments given by mujoco but I am confused on how to actually code.

Anyways, Thank you. I will work with what I know.