ikostrikov pytorch-trpo issues

ikostrikov / pytorch-trpo

PyTorch implementation of Trust Region Policy Optimization

MIT License

433 stars 91 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

It seems that the importance sampling code part is wrong.

#22 yhy258 opened 1 year ago
2
what is shs?

#21 YUYING07 opened 1 year ago
0
Idon‘t konw what the “neggdotstepdir” for ，Thanks ！！！

#20 baywc568 opened 3 years ago
0
Object oriented

#19 GittiHab opened 4 years ago
0
What and When to send on the GPU?

#18 prathamesh0 closed 4 years ago
1
Bootstrapping the value function?

#17 XuchanBao opened 5 years ago
1
Main.py line128

#16 ArtificialIntelligenceRobot closed 5 years ago
0
dose the linesearch method conflict with a "trust region" policy gradient algorithm?

#15 nuomizai opened 5 years ago
1
The step of t is not necessary in main.py

#14 LeonardPatrick opened 6 years ago
0
Is the get_kl() function correct?

#13 zzzxxxttt closed 6 years ago
0
what does volatile=True for?

#12 dragen1860 closed 6 years ago
1
The get_kl function returns 0 always.

#11 mkbera closed 6 years ago
1
Multiprocess

#10 mavenlin closed 6 years ago
0
doc?

#9 hughperkins closed 6 years ago
4
compute the Fisher-Vector Producy

#8 ghost closed 6 years ago
1
other env

#7 ghost closed 6 years ago
1
have you verified the code's correctness?

#6 xinleipan closed 6 years ago
1
Various fixes

#5 Kaixhin closed 7 years ago
0
Use pytorch 0.2.0?

#4 onlytailei closed 7 years ago
1
Have you tested it on the Atari games?

#3 onlytailei closed 7 years ago
6
What is get_kl() doing in main.py?

#2 jtoyama4 closed 7 years ago
12
How to modify the code for discrete actions?

#1 ghost closed 7 years ago
3