ikostrikov pytorch-a3c issues

ikostrikov / pytorch-a3c

PyTorch implementation of Asynchronous Advantage Actor Critic (A3C) from "Asynchronous Methods for Deep Reinforcement Learning".

MIT License

1.23k stars 279 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

where see the result？

#80 xbdeng opened 1 year ago
0
if there's no "if shared_param.grad is not None: return" what will happen?

#79 yinqinghai opened 1 year ago
1
TypeError: tuple indices must be integers or slices, not tuple

#78 JingYuPrime opened 1 year ago
0
Can you provide the python, pytorch, numpy and other versions used in the project?

#77 LongLongLongWayToGo opened 2 years ago
0
Scepticism about the correctness of the use of the LSTMCell

#76 alirezakazemipour opened 2 years ago
0
After some steps, all the NNs always output same action

#75 Eify666666 opened 3 years ago
1
Stuck in 'p.join()'

#74 RickWangww opened 4 years ago
1
Dependency list not provided (environment.yml file)

#73 MasterScrat opened 4 years ago
0
Why do we reverse rewards?

#72 npitsillos opened 4 years ago
1
How does A3C aggregate the model from different learner?

#71 dxu23nc opened 4 years ago
1
with respect to how to choose an action

#70 obitoquilt opened 4 years ago
0
Question in train.py

#69 verystrongjoe opened 5 years ago
0
rename observation method

#68 briantimar opened 5 years ago
0
[Question] Does a2c support distributed processing?

#67 QiXuanWang opened 5 years ago
0
NotImplementedError

#66 ebasatemesgen opened 5 years ago
6
The while True loop of function train?

#65 machanic opened 5 years ago
0
Multi-processing or multi-threading

#64 lingzhang0319 opened 5 years ago
1
Reward Smoothing

#63 WangChen100 closed 5 years ago
0
What's the difference between environment 'Pong-v4' and 'PongDeterministic-v4'

#62 HuiSiqi opened 5 years ago
0
Renamed args.tau to args.gae_lambda

#61 beduffy closed 5 years ago
0
GAE parameter name should be lambda not tau. And why is default 1.0?

#60 beduffy closed 5 years ago
4
gradient share problem

#59 vergilus closed 5 years ago
1
Did lstm cell really make more sense in A3C?

#58 WonderSeven opened 6 years ago
1
big bug

#57 harini20 closed 6 years ago
1
Why is the convergence on Pong so fast?

#56 Omegastick closed 6 years ago
1
how to under ensure ensure_shared_grads?

#55 luochao1024 opened 6 years ago
1
no warning (gym & pytorch0.4 warnings)

#54 mohamad-hasan-sohan-ajini opened 6 years ago
0
action_space.n and actions sampling

#53 bionick87 closed 6 years ago
0
Cant' work on pytorch 0.4.0

#52 jiakai0419 closed 6 years ago
8
No framestack?

#51 lweitkamp closed 6 years ago
0
Atari Environment Decision Choice

#50 choinker closed 6 years ago
1
is ensure_shared_grads still required?

#49 edbeeching closed 6 years ago
6
environment observation normalization

#48 yhcao6 closed 6 years ago
1
changed reshape to moveaxis

#47 atgambardella closed 6 years ago
1
Can't work on Ubuntu 16.04

#46 caozhenxiang-kouji opened 6 years ago
22
Question about normalized_columns_initializer(weights, std=1.0) method.

#45 xueyaohuang closed 6 years ago
0
GPU version of a3c algorithm?

#44 bearpaw closed 6 years ago
2
Works better with 80x80 images

#43 ShaniGam closed 6 years ago
0
Mixture of model prediction and update

#42 dohnala closed 6 years ago
4
Where does the initializer come from?

#41 zhengsx closed 7 years ago
3
Running with pytorch 0.2.0

#40 ShaniGam closed 7 years ago
10
when run this code in macbook pro, python exit unnormally

#39 yyhTHU closed 7 years ago
2
File "main.py", line 55,TypeError: sum received an invalid combination of arguments

#38 happykayy closed 7 years ago
4
When using no-shared = False, the process is blocked

#37 keithyin opened 7 years ago
10
I cannot train with your recent pytorch-a3c

#36 aizawatkm closed 7 years ago
12
Fix episode_length increment

#35 nadavbh12 closed 7 years ago
0
question about using GAE

#34 andrewliao11 closed 7 years ago
1
What is the purpose of `os.environ['OMP_NUM_THREADS'] = '1'`?

#33 xmfbit closed 7 years ago
1
Error when rendering

#32 ShaniGam closed 7 years ago
0
Question about the policy loss calculation?

#31 hyparxis closed 7 years ago
0