miyosuda async_deep_reinforce issues

miyosuda / async_deep_reinforce

Asynchronous Methods for Deep Reinforcement Learning

Apache License 2.0

592 stars 192 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Request for a python code for cartpole problem

#55 Shafafcp opened 1 year ago
0
python code for cartpole problem using q-learning

#54 Shafafcp closed 1 year ago
0
111

#53 yangxin-1124 opened 3 years ago
0
built environment

#52 Jaylyn-s opened 5 years ago
0
Add interface to pass inter and intra parameters

#51 opencici2006 opened 6 years ago
0
how do I do inference?

#50 suntao2012 opened 6 years ago
0
Incorrect policy loss

#49 takuseno closed 7 years ago
1
code does not work for breakout

#48 1601214542 opened 7 years ago
0
RMRProp and use_locking = False

#47 MogicianWu opened 7 years ago
0
ValueError: Variable net_-1/basic_lstm_cell/weights does not exist, or was not created with tf.get_variable(). Did you mean to set reuse=None in VarScope?

#46 Jiankai-Sun opened 7 years ago
2
fix typo

#45 xiaoschannel closed 4 years ago
1
Update algorithm works not correct?

#44 Maschwe opened 7 years ago
0
Merge pull request #1 from miyosuda/master

#43 jsikyoon opened 7 years ago
0
I have three issues about A3C-lstm

#42 vincenschan opened 7 years ago
0
why recalculate pi and v?

#41 joyousrabbit opened 7 years ago
1
some issues about running it on windows10

#40 vincenschan opened 7 years ago
0
locking global_t when incrementing? not thread-safe?

#39 gabrieledcjr closed 7 years ago
0
Updated for tensorflow 1.0, support for Mnih 2015 network architecture

#38 gabrieledcjr opened 7 years ago
0
Hogwild?

#37 gabrieledcjr opened 7 years ago
0
Minimal action for Pong is now 6 based from ALE

#36 gabrieledcjr opened 7 years ago
1
I can't train with the other games.

#35 Michi-123 closed 5 years ago
4
build problems about #cmake -DUSE_SDL=ON -DUSE_RLGLUE=OFF -DBUILD_EXAMPLES=OFF .

#34 4575759ww opened 7 years ago
1
About variable error.

#33 Michi-123 closed 5 years ago
3
Variable net_-1/BasicLSTMCell/Linear/Matrix does not exist, or was not created with tf.get_variable().

#32 nanxintin closed 7 years ago
3
Problem with compiling the code

#31 Gin8787 opened 7 years ago
1
Pong's minimal action set. I can't gain scores more than -21 using the first three ones.

#30 NoListen closed 7 years ago
1
Training speed (in hours)

#29 tgangwani opened 7 years ago
0
A3C-FF seems not work well?

#28 pengsun opened 7 years ago
9
use Multiprocessing instead of Threading?

#27 mw66 opened 7 years ago
3
Would like to convert this to Keras but having issues

#26 rnunziata opened 7 years ago
0
Binary files for other games?

#25 wsjeon closed 7 years ago
2
Any reason for choosing ACTION_SIZE = 3? Extension for continuous action?

#24 wsjeon closed 7 years ago
2
Update for TF 0.12.

#23 wsjeon closed 7 years ago
1
Error occurs at recent TensorFlow 0.12

#22 wsjeon closed 7 years ago
2
Why you are use custom gradint appiler?

#21 dm-mch opened 7 years ago
1
how to see the training progress graph?

#20 mw66 closed 7 years ago
6
Any Chance or plans of adding MULTI-GPU for training

#19 developeralgo8888 opened 8 years ago
0
A3C-LSTM and DRQN

#18 IbrahimSobh opened 8 years ago
1
Scores are not averaged using global network unlike the original paper

#17 IbrahimSobh opened 8 years ago
0
running speed with different number of threads

#16 skaae opened 8 years ago
1
Failing to fully replicate Pong with A3C-LSTM

#15 revilokeb opened 8 years ago
11
Correct width/height transposition in game_state

#14 yieldthought closed 7 years ago
2
should add signal.pause() before thread-joining in a3c.py

#13 congling closed 8 years ago
0
question about loss wrt gradient

#12 apeterswu closed 8 years ago
0
about steps related to the reward

#11 congling opened 8 years ago
6
Change code for a different problem

#10 gowthamnatarajan opened 8 years ago
5
how to test the model?

#9 apeterswu opened 8 years ago
19
Changed A3C networks to Nature paper version

#8 sahiliitm closed 7 years ago
5
Running speed

#7 tokb23 opened 8 years ago
5
Breakout

#6 Itsukara closed 7 years ago
6