KO
|
EN
gitlite — search
Search
#python
#java
#python3
#arduino
#golang
#machine-learning
#rust
#html
#flask
#javascript
#seismology
#nodejs
pytorch_MINERVA
★ 13
Open GitHub ↗
No description available.
Download README (.md)
Explore Similar Repositories
Multi-Attention-Recurrent-Network---MARN-AAAI2018
:
Implementation of MARN AAAI18 in pytorch
docker-tutorial
:
Tutorial Docker. Usado em palestras.
nestjs-mailer
:
Mailer module for NestJS
rhc
:
Implementation of Receding Horizon Curiosity Algrithm
unity-rhythm-engine
:
A template project for creating rhythm games in Unity.
// repository documentation
Was this content helpful?
★ 0
(0 ratings)
Select Rating:
★
★
★
★
★
Submit Feedback
Recent Feedback
×
Download README
Do you want to download the
README.md
file for
pytorch_MINERVA
?
Download (.md)
# pytorch_MINERVA This is the code for the paper [Go for a Walk and Arrive at the Answer - Reasoning over Paths in Knowledge Bases using Reinforcement Learning](https://arxiv.org/abs/1711.05851) in pytorch version. I try to reproduce the model with pytorch and use WN18RR for testing. But I cannot achieve the same performance as the tensorflow version. It will be very helpful if someone use my code and find why my implementation is worse than the original version or to provide another pytorch implementation with better performance. The tensorflow version provided by the author is located at https://github.com/shehzaadzd/MINERVA. ## Quick start The following command starts our model. You can view main.py for changing parameters. ``` python src/main.py ``` ## Evaluation ## Requirements - Python 3.6 - Numpy - pytorch 1.0
