yaserkl RLSeq2Seq issues

yaserkl / RLSeq2Seq

Deep Reinforcement Learning For Sequence to Sequence Models

https://arxiv.org/abs/1805.09461

MIT License

767 stars 160 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Bump tensorflow-gpu from 1.10 to 2.12.0

#46 dependabot[bot] opened 1 year ago
0
Bump tensorflow-gpu from 1.10 to 2.9.3

#45 dependabot[bot] closed 1 year ago
1
Bump tensorflow-gpu from 1.10 to 2.7.2

#44 dependabot[bot] closed 1 year ago
1
Bump tensorflow-gpu from 1.10 to 2.6.4

#43 dependabot[bot] closed 2 years ago
1
Bump tensorflow-gpu from 1.10 to 2.5.3

#42 dependabot[bot] closed 2 years ago
1
Bump tensorflow-gpu from 1.10 to 2.5.1

#41 dependabot[bot] closed 2 years ago
1
Bump tensorflow-gpu from 1.10 to 2.3.1

#40 dependabot[bot] closed 3 years ago
1
Bump tensorflow-gpu from 1.10 to 1.15.4

#39 dependabot[bot] closed 3 years ago
1
Replay Buffer isnt Loaded Enough Yet

#38 Fatman003 opened 4 years ago
5
Error when decoding

#37 theago-ls closed 4 years ago
0
Bump tensorflow-gpu from 1.10 to 1.15.2

#36 dependabot[bot] closed 3 years ago
1
Bump tensorflow-gpu from 1.10 to 1.15.0

#35 dependabot[bot] closed 4 years ago
1
Possible shaping error on _add_loss_op() in model.py

#34 thefirebanks opened 5 years ago
1
Working in google colab

#33 sunny-Ne5 opened 5 years ago
1
scheduled sampling OOV issue

#32 rajeev595 opened 5 years ago
0
Why is the training time on pointer-generator with the same hyperparameters 4 times the original paper (https://arxiv.org/abs/1704.04368) ?

#31 xiangriconglin closed 5 years ago
0
Trying to emulate "A Deep Reinforced Model for Abstractive Summarization", trying to find where in code greedy/sampled distribution implemented

#30 Santosh-Gupta closed 5 years ago
3
two many arguments on calc_reward

#29 TiagoMRodrigues opened 5 years ago
0
Maybe interested in these papers?

#28 khanhptnk opened 5 years ago
0
How to apply the trained model

#27 git4sun opened 5 years ago
0
Transfer learning

#26 nickluijtgaarden closed 5 years ago
2
Early stopping based on evaluation results

#25 perprit closed 5 years ago
2
Facing a issue while training for NMT ?

#24 yashkumaratri closed 5 years ago
0
cannot reproduct the reuslt in pointer-generator with coverage mechanism, always inferior to pgen model.

#23 gm0616 opened 5 years ago
4
when convert to RL model something wrong

#22 zhangxiaoyidog closed 5 years ago
2
Question on the Conditional Probability of RL Loss

#21 crystina-z opened 5 years ago
1
A problem about Q updates

#20 painterner opened 5 years ago
0
Can the if statement of line 382 of the attention_decoder.py be removed?

#19 CXX1113 closed 5 years ago
3
Why doesn't line352 of attention_decoder.py need to reuse the variable of this function like line347?

#18 CXX1113 closed 5 years ago
4
when decoding，something wrong.

#17 ljsun opened 5 years ago
15
Question about the implementation of self-critic policy gradient reinforcement learning

#16 Weili-NLP closed 5 years ago
4
Summarization pipeline

#15 chmille3 closed 5 years ago
6
CPU version of tensorflow

#14 chmille3 closed 5 years ago
1
Data pre-processing questions

#13 twoflypig closed 5 years ago
1
How to train a NMT model ?

#12 kobenaxie closed 6 years ago
3
can you offer your pretrain model?

#11 457138317 opened 6 years ago
5
OOM when run the task

#10 linbojin closed 6 years ago
5
Update to Python 3.5 & CUDA 9 and TensorFlow 1.10 lastest version

#9 astorfi closed 6 years ago
0
about attention_decoder.py

#8 jimmyljxy closed 6 years ago
0
ImportError: No module named newspaper

#7 lan2720 closed 6 years ago
1
device

#6 astorfi closed 6 years ago
0
check

#5 astorfi closed 6 years ago
0
TensorFlow adaption

#4 astorfi closed 6 years ago
0
Evaluation results in comparison to Seq2Seq without RL

#3 shahbazsyed closed 6 years ago
1
Python 3 issues.

#2 cclauss closed 6 years ago
1
beam search decoder

#1 lsq357 closed 6 years ago
1