Comments (6)
@misaki-sysu RL suffers from the cold start problem in a large-scale state or action space so that it can hardly learn from the sparse reward, especially for hierarchical RL in such a complex task. So pretraining can prevent the agent from exploring many unreasonable cases (e.g. multiple source entities in one relational triple) thus making the training possible.
from hrl-re.
Did you pretrain the model first? e.g.
python3 main.py --datapath ../data/NYT10/ --pretrain True
Please refer to #1 for the results of pretraining
from hrl-re.
@truthless11 this result I mention above had no pretrain. I had pretrained it and the accuracy , F1 score stayed 1 while pretraining, is it normal?
from hrl-re.
Yes, it is. When pretraining, the output of training data is useless as it will always print out 1.0 F1 score. Please be patient and wait for the output of test data.
from hrl-re.
Thanks! I will wait for the pretrain result.
But, forgive my ignorance, why can't I just train the model without pretraining ?
from hrl-re.
Thanks for you answer!
from hrl-re.
Related Issues (19)
- Pretraining works fine, but rl training stays at 0 Accuracy HOT 10
- Confusion on Evaluation Metrics HOT 1
- where is train.json HOT 2
- NYT10 Original Data HOT 1
- have u compared with the “Robust Distant Supervision Relation Extraction via Deep Reinforcement Learning”? HOT 1
- Dear author, i have read you paper and conduct your codes, there is a question that how you get the triplets ? In the codes, you just validate the dev and test datasets, and your code dont't caculate the metrics of real triplest strictly. Can you can answer my doubts? Thanks .
- How to deal with the words with low frequency (only appearing one or two times)? HOT 1
- Why do I report errors when using CPU methods for training HOT 10
- Relation indicator questions HOT 1
- How can I solve the following problems?IndexError: Dimension out of range (expected to be in range of [-1, 0], but got 1) HOT 1
- Hello,author.Why do you train and test your model on nyt10?
- Question about data preprocess HOT 3
- hi,
- Replace LSTM with Bert HOT 5
- hardware requirements HOT 1
- multi processes problem HOT 1
- What does the "tags" mean in key "relations" of data? HOT 4
- Is there a preprocess scripts available here? HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from hrl-re.