issues
search
marlbenchmark
/
on-policy
This is the official implementation of Multi-Agent PPO (MAPPO).
https://sites.google.com/view/mappo
MIT License
1.27k
stars
292
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
algorithms in MPE don't have policy.actor and policy.critic
#115
h1657
opened
1 week ago
0
Update on-policy to work with pettingzoo environment
#114
conor-wallace
closed
2 weeks ago
0
fix: r_mappo & mat buffer factor unpack
#113
HosnLS
closed
2 months ago
0
MAPPO simple spread not converging
#112
zhangmingcheng28
opened
2 months ago
2
Master
#111
Malhaar-k
closed
3 months ago
0
Can't the mat algorithm be called yet?
#110
BUCK111111
closed
3 months ago
1
Cannot reproduce MPE simple_speaker_listener
#109
AlbertoSinigaglia
opened
4 months ago
2
求助FP和AS状态!!
#108
1999Zzh
closed
4 months ago
1
fixed bug in initializing ValueNorm
#107
Nikunj-Gupta
closed
4 months ago
0
shared_buffer.py is an outdated file
#106
sixie10
closed
4 months ago
0
Does the state of the grid world need to be normalized?
#105
saiyuhang123
closed
2 months ago
1
Why share_obs in shared/mpe_runner.py just repeats obs when self.use_centralized_V set to true
#104
Jaroan
closed
2 months ago
1
无法解析导入“wandb”
#103
jun-running
opened
6 months ago
1
Action mask!
#102
shushushulian
opened
7 months ago
1
Shape of buffered log_probs
#101
Maxtoq
opened
7 months ago
0
'on-policy\onpolicy\scripts\train_smac_scripts\train_smac_8m_vs_9m.sh' training script file bug fix
#100
JensenLZX
closed
7 months ago
0
Model...
#99
bitbjt
closed
2 months ago
1
Error when run ./train_mpe_spread.sh
#98
ChuangZhang1999
opened
8 months ago
2
When I tried to train the code for smacv2, I encountered this error message——AssertionError: check recurrent policy!
#97
chenzihan1
closed
2 months ago
1
NAN
#96
lgzid
closed
9 months ago
2
Update Overcooked
#95
Aidilele
closed
9 months ago
0
missing "onpolicy.runner.separated.hanabi_runner_forward"
#94
AlbertoSinigaglia
closed
2 months ago
1
question about reply buffer size in MAPPO
#93
Gloriabhsfer
opened
10 months ago
0
请问我该如何保存replay?
#92
BUPT-zeld151
opened
11 months ago
0
模型性能问题
#91
bitbjt
closed
11 months ago
3
HAPPO为何与mappo的policy文件完全相同
#90
strivebfq
closed
11 months ago
0
Runtime Error: Tensors on Different Devices (cuda:0 and cpu)
#89
itstyren
closed
11 months ago
1
add if stmt to handle Policy constructor calling
#88
colourfulspring
closed
10 months ago
0
__init__() got multiple values for argument 'device'
#87
colourfulspring
opened
1 year ago
2
fix smacv2 dones bugs and a type bug
#86
jason-huang03
closed
1 year ago
0
Doubts about the results of rmappo/mappo in SMAC
#85
linshi9658
closed
11 months ago
1
render_mpe produces much worse performance than training or evaluation
#84
wenshuaizhao
closed
1 year ago
2
Questions on the episode length of 1000 on gfootball env instead of a maximum env limit of 400
#83
DeeDive
opened
1 year ago
1
add other marl algorithms
#82
Sapio-S
closed
1 year ago
0
Fixed render errors
#81
XHN-1
closed
9 months ago
0
Update shared_buffer.py
#80
HosnLS
closed
1 year ago
0
reder问题
#79
sdabj
closed
11 months ago
1
How to caculate rewards in MARL environments?
#78
BUPT-zeld151
closed
11 months ago
1
Modify action space creation (MPE)
#77
XHN-1
closed
1 year ago
0
Update README.md on installation guideline
#76
DeeDive
closed
1 year ago
0
add smacv2 scripts
#75
Sapio-S
closed
1 year ago
0
No smac_runner in the separated file
#74
Precola
closed
11 months ago
1
How to speed up training on hanabi
#73
yanxue7
closed
1 year ago
1
bug in football_runner.py
#72
Random8756
closed
9 months ago
1
the value for the available_actions
#71
EddyJason
opened
1 year ago
3
The running for the simple_speaker_listener
#70
EddyJason
closed
11 months ago
1
Wrong with the reward in the simple_speaker_listener.py
#69
EddyJason
closed
11 months ago
1
MatplotlibDeprecationWarning
#68
EddyJason
closed
1 year ago
1
terminal error-render_mpe.sh
#67
EddyJason
closed
1 year ago
5
gfootball win_rate calculation
#66
wenshuaizhao
closed
1 year ago
3
Next