issues
search
rgilman33
/
simple-A2C-PPO
Actor-critic trained w PPO on OpenAI's Procgen Benchmark (PyTorch). Built from scratch.
100
stars
26
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Question about computing generalized advantage estimation
#5
blahBlahhhJ
closed
11 months ago
0
"Runtime Error: view size is not compatible with input tensor's size and stride"
#4
kgkolias
opened
4 years ago
1
Which version of torch are you using?
#3
Michi-123
closed
4 years ago
1
TypeError: multinomial() missing 1 required positional arguments: "num_samples"
#2
inkplay
opened
5 years ago
1
critic and actor have same hidden layers
#1
pjcorp
opened
6 years ago
1