Skip to content

justinjfu/exemplar_models

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Exemplar Models

This repository contains an implementation of exemplar models for the purpose of approximate density estimation.

The model is detailed in the following paper:

EX2: Exploration with Exemplar Models for Deep Reinforcement Learning

Justin Fu*, John D. Co-Reyes*, Sergey Levine. NIPS 2017

Setup

This library requires Numpy, Scipy, Tensorflow, and Matplotlib.

Running the Code

To run the demo code, simply run the following script:

python scripts/twod_example.py

This will save a series of images taken over the course of training into the data folder. The model's estimates are shown in the left panel, and the ground truth data is shown on the right.

Iteration 1000:

1000

Iteration 10000:

10000

Iteration 20000:

20000

Iteration 30000:

30000

About

Exemplar models for approximate density estimation

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages