openai maddpg issues - Githubissues

openai / maddpg

Code for the MADDPG algorithm from the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"

https://arxiv.org/pdf/1706.02275.pdf

MIT License

1.65k stars 494 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Error when setting display to true

#31 njfdiem opened 5 years ago
3
TypeError: set_color() got multiple values for argument 'alpha' in Simple-Crypto

#30 marwanihab opened 5 years ago
6
TypeError: must be str, not NoneType . run train.py

#29 SHYang1210 closed 5 years ago
2
Nontype flaw in "train.py", line 182

#28 DailinH opened 5 years ago
3
Can this algorithm be generalised to work with multiple (60) agents competing against eachother?

#27 alexanderkell closed 3 years ago
2
Cumulative rewards are not promoted when use MADDPG

#26 jhcknzzm opened 5 years ago
0
use tf.layers and add gpu_options.allow_growth=True

#25 GoingMyWay closed 5 years ago
0
update README with repo status

#24 christopherhesse closed 6 years ago
0
The result is not that ideal like the paper showed

#23 Jarvis-K opened 6 years ago
3
Having trouble with import maddpg

#22 ishanivyas opened 6 years ago
1
Please add a description to this repo

#21 clintonyeb opened 6 years ago
0
Calculating Success Rate for Physical Deception

#20 ZishunYu closed 6 years ago
1
Q divergence

#19 rbrigden opened 6 years ago
0
How or why the gaussian distribution contributes to the training?

#18 Chen-Joe-ZY opened 6 years ago
4
Import Errors

#17 murtazarang closed 3 years ago
6
How maddpg update actor?

#16 newbieyxy closed 6 years ago
0
Error in scenario simple_reference with gym.spaces.MultiDiscrete

#15 hcch0912 closed 6 years ago
1
displaying agent behaviors on the screen

#14 williamyuanv0 closed 6 years ago
1
When I run train.py,it shows "TypeError: Can't convert 'NoneType' object to str implicitly".

#13 seahawkk closed 6 years ago
4
Cannot reproduce experiment results

#12 arbaazkhan2 closed 6 years ago
3
The reward and action is nan ?

#11 xuemei-ye closed 6 years ago
3
How can i use it for "simple_world_comm" in MPE? ---- "AssertionError: nvec should be a 1d array (or list) of ints"

#10 zimoqingfeng closed 6 years ago
1
action exploration & Gumbel-Softmax

#9 djbitbyte opened 6 years ago
9
It seems that you don't use "Policy ensembles" and "Inferring policies of other agent" in this code?

#8 pengzhenghao closed 6 years ago
2
It seems that the training is decentralized?

#7 pengzhenghao closed 6 years ago
1
Running train.py doesn't seem to work

#6 suryabhupa closed 6 years ago
5
when I run train.py,it shows "module 'tensorflow' has no attribute 'float32'"

#5 williamyuanv0 closed 6 years ago
8
add multiagent-particle-envs to PYTHONPATH

#4 djbitbyte closed 6 years ago
4
fix some miss

#3 wwxFromTju closed 6 years ago
0
rnn_]cell=None is a Syntax Error in both Python 2 and 3

#2 cclauss closed 6 years ago
1
Remove pycache and add gitignore

#1 himanshub16 closed 6 years ago
0