issues
search
daisatojp
/
mpo
PyTorch Implementation of the Maximum a Posteriori Policy Optimisation
GNU General Public License v3.0
70
stars
19
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
How should the hyperparameter alpha be set?
#16
formoree
opened
2 months ago
0
Update for pytorch and gym v0.26.0 breaking change.
#15
zhenpingfeng
closed
1 year ago
0
Is there a single book or online course you would recommend to begin to comprehend this repo?
#14
MotorCityCobra
opened
2 years ago
0
Does this MPO code support custom environments?
#13
Arcadianlee
opened
2 years ago
1
Clipping self.α_μ and self.α_Σ in continuous action space
#12
albertbou92
opened
3 years ago
1
negative determinant for Σ
#11
nilsplettenberg
closed
3 years ago
3
Question: Minimization of dual function
#10
vinerich
opened
3 years ago
2
fix #8
#9
daisatojp
closed
3 years ago
0
Make more informative
#8
daisatojp
closed
3 years ago
0
Question: on loss_p calculation
#7
vinerich
opened
3 years ago
5
fix
#6
daisatojp
closed
4 years ago
0
decouple
#5
daisatojp
closed
4 years ago
0
dev_t2
#4
daisatojp
closed
4 years ago
0
fix #1
#3
daisatojp
closed
4 years ago
0
learn Discrete Action Space
#2
daisatojp
closed
4 years ago
0
Retrace Algotithm
#1
daisatojp
closed
4 years ago
2