๐ [Under Review] "Symbolic Visual Reinforcement Learning: A Scalable Framework with Object-Level Abstraction and Differentiable Expression Search", Wenqing Zheng*, S P Sharan*, Zhiwen Fan, Kevin Wang, Yihan Xi, Atlas Wang
when I run gplearn_optuna.py,then
AttributeError: module 'numpy' has no attribute 'int'. np.int was a deprecated alias for the builtin int. To avoid this error in existing code, use int by itself. Doing this will not modify any behavior and is safe. When replacing np.int, you may wish to use e.g. np.int64 or np.int32 to specify the precision. If you wish to review your current use, check the release note link for additional information.
The aliases was originally deprecated in NumPy 1.20; for more details and guidance see the original release note at: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
when I use :python main.py --task train --config configs/atari_spaceinvaders.yaml resume True device 'cuda:0'
then the following error happened:
Traceback (most recent call last):
File "main.py", line 1, in
from engine.utils import get_config
File "/home/l/Downloads/DiffSES/space/engine/utils.py", line 4, in
from space.config import cfg
ModuleNotFoundError: No module named 'space'
This is a wonderful code repository with many impressive capabilities. I sincerely appreciate you sharing it.
When testing the code, I noticed the section for utilizing the OD module to extract velocity and position in[save_offline_dataset.py]&[symbolic_finetuning_guided.py] does not seem to be included, so do as the "save teacher dataset" code. If it's not too much trouble, adding that code would significantly improve the functionality. Please let me know if you would be willing to add it at your convenience.
Thank you again for providing this great resource. Your work is incredibly valuable to the community. I look forward to seeing future updates!
when I run distill_teacher.py, then
Traceback (most recent call last):
File "/home/l/Downloads/DiffSES/distill_teacher.py", line 63, in
logical = make_function(function=_logical, name="logical", arity=2)
File "/home/l/Downloads/DiffSES/gplearn/functions.py", line 99, in make_function
raise ValueError("supplied function %s does not return a numpy array." % name)
ValueError: supplied function logical does not return a numpy array.