joeybose / florl Goto Github PK

Hi @joeybose ,

I tried your commands in this file: https://github.com/joeybose/FloRL/blob/flows/pytorch-soft-actor-critic/runFlows.sh
It seemed that your programs do not learn. Do you have records of running these commands?

Thanks!

hi！thank you for your code，when I run “policy=Flow” get error.Can you help me ，thank you so much！！
(ff) E:\codeRL\FloRL-master\pytorch-soft-actor-critic>python main.py --namestr=G-S-DG-CG --make_cont_grid --batch_size=128 --replay_size=100000 --hidden_size=64 --num_steps=100000 --policy=Flow --smol --comet --de
nse_goals --silent
E:\software\anaconda3\envs\ff\lib\site-packages\gym\logger.py:30: UserWarning: WARN: Box bound precision lowered by casting to float32
warnings.warn(colorize('%s: %s'%('WARN', msg % args), 'yellow'))
COMET WARNING: Unknown output logging mode: None, fallbacking on basic output logging
COMET ERROR: Failed to set run source code
COMET INFO: Experiment is live on comet.ml https://www.comet.ml/florl/florl/5cb5d85673b848dab6ffef503d55b59a

Traceback (most recent call last):
File "main.py", line 287, in
main(args)
File "main.py", line 140, in main
action_batch,reward_batch,next_state_batch,mask_batch, updates)
File "E:\codeRL\FloRL-master\pytorch-soft-actor-critic\sac.py", line 260, in update_parameters
policy_loss.backward()
File "E:\software\anaconda3\envs\ff\lib\site-packages\comet_ml\monkey_patching.py", line 292, in wrapper
return_value = original(*args, **kwargs)
File "E:\software\anaconda3\envs\ff\lib\site-packages\torch\tensor.py", line 195, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph)
File "E:\software\anaconda3\envs\ff\lib\site-packages\torch\autograd_init_.py", line 99, in backward
allow_unreachable=True) # allow_unreachable flag
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.FloatTensor [128, 2]], which is output 0 of struct torch::autograd::CopySlices, is at version 2;
expected version 1 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).

If you suspect this is an IPython 7.13.0 bug, please report it at:
https://github.com/ipython/ipython/issues
or send an email to the mailing list at [email protected]

You can print a more detailed traceback right now with "%tb", or use "%debug"
to interactively debug it.

Extra-detailed tracebacks for bug-reporting purposes can be enabled via:
%config Application.verbose_crash=True

COMET INFO: ----------------------------
COMET INFO: Comet.ml Experiment Summary:
COMET INFO: Data:
COMET INFO: url: https://www.comet.ml/florl/florl/5cb5d85673b848dab6ffef503d55b59a
COMET INFO: Other [count]:
COMET INFO: Name: G-S-DG-CG
COMET INFO: ----------------------------
COMET INFO: Uploading stats to Comet before program termination (may take several seconds)