Closed dehezhang2 closed 1 year ago
I am also getting a similarly offset of 0.009954251707404079.
As a side question, does the calculation of your torque work for the dog gaussian and the human reward?
The torque part can pass the test.
I also encountered the same issue.
Obtained: 0.00995425170740408 Expected: 0.009990833552124415 ± 1.0e-08
There was a small error creating the test case for Bob. I'm training Bob again to make sure that everything works.
I will update that test case during the day.
Download this file and put it under src/src/python/tests/pickled_files/
.
Add the file to the repo using: git add test_data_bob1679334591.29026.pickle
Update the variable pickle_path
in line 8
of src/python/tests/03_test_human_reward.py
to reflect the changes i.e:
pickle_path = '/pickled_files/test_data_bob1679334591.29026.pickle'
Commit and push the changes. Correct implementations should pass the test.
Should we also change the directory in line 8
of the file ./src/python/tests/03_test_human_reward.py
?
Yes. Please update the variable pickle_path
in line 8 of src/python/tests/03_test_human_reward.py
to reflect the changes i.e:
pickle_path = '/pickled_files/test_data_bob1679334591.29026.pickle'
Do you also change the number of joints from 43 to 44? I pass the test if I choose 44, but in Readme the variable is requested to be 43.
@drlxj The actual number of joints is 44. I just fixed the typo on the README.
May I ask a question about the joint angle calculation? It seems that my calculation has a small error:
In the task description, the number of joints is 43, but in the
ObservationData
class the size of thejoint_angles
array is 44. Is it possible that this mismatch caused the error?