Closed sven1977 closed 1 year ago
Also happens in APPO and I assume in all async algorithms. Any progress?
The same for the PyTorch version of IMPALA.
I ran into this issue again. Is there any progress? Could you add at some clear error that it is not supported?
IMPALA (TensorFlow) crashes with
IndexError: index 138 is out of bounds for axis 0 with size 132
if using an RNN andnum_sgd_iter > 1
.config:
Repro Script:
Ray version and other system information (Python version, TensorFlow version, OS):
Reproduction (REQUIRED)
Please provide a script that can be run to reproduce the issue. The script should have no external library dependencies (i.e., use fake or mock data / environments):
If we cannot run your script, we cannot fix your issue.