-
Deer author, have you do some tests about continuous actions space envs? Can i let 'continuous=True'? After i use continuous actions space envs to test, it shows that 'action_optimizer.param_groups[0]…
-
Hi, I am try reproducing results and have following issue in "sqddpg_33_0_l1.out" while doing "source train_case33.sh 0 l1 reproduction"
Traceback (most recent call last):
File "train.py", l…
-
Thank you very much for updating the code! You have fix matd3 and sqddpg，but not fix the ''model.py'' file.
-
Excuse me, do you have code for multi particle environment?
-
Hi,
Thank you for you sharing. I tried to run your SQDDPG program. I installed all packages as you recommended. But I cannot run it successfully. Python reported that aux has many syntax errors. I …
-
Hi,
Would anybody help on this issue?
I am running the train.py to see the scenario simple_tag with maddpg, and have modified model_name = 'maddpg' in arguments.py
the error pops up:
Tracebac…
-
Dear Jianhong:
I'm so honored to read this excellent article which is very helpful for me to start with credit assignment in cooperative multi-agent reinforcement learning. However, unfortunately, I'…
-
The 'logist' refers to log prob, but LICA use the output of DNN as 'logist'.
see https://github.com/shaabhishek/gumbel-softmax-pytorch/blob/master/Categorical%20VAE.ipynb
-
Hi,
Thanks for open sourcing your work! At the moment, I'm trying to reproduce Table 2 of your paper for traffic_junction medium settings; however, my reproduced numbers are only around 70% as oppo…