资源分类
》 资源 》算法》ppo_pytorch_cpp

ppo_pytorch_cpp

2019-09-10 | |  147 |   0 |   0

PPO Pytorch C++

This is an implementation of the proximal policy optimization algorithm for the C++ API of Pytorch. It uses a simple TestEnvironment to test the algorithm. Below is a small visualization of the environment, the algorithm is tested in.


test_mode.gif

Fig. 1: The agent in testing mode.




Build

You first need to install PyTorch. For a clean installation from Anaconda, checkout this short tutorial, or this tutorial, to only install the binaries.

Do

mkdir build
cd build
cmake -DCMAKE_PREFIX_PATH=/absolut/path/to/libtorch ..
make

Run

Run the executable with

cd build
./train_ppo

It should produce something like shown below.


epoch_1.gifepoch_10.gif

Fig. 2: From left to right, the agent for successive epochs in training mode as it takes actions in the environment to reach the goal.




The algorithm can also be used in test mode, once trained. Therefore, run

cd build
./test_ppo

Visualization

The results are saved to data/data.csv and can be visualized by running python plot.py.


上一篇：Asynchronous Advantage Actor-Critic in PyTorch

下一篇：PyTorch Image Classification with Kaggle Dogs vs Cats Dataset

用户评价
全部评价

热门资源

  • Keras-ResNeXt

    Keras ResNeXt Implementation of ResNeXt models...

  • seetafaceJNI

    项目介绍 基于中科院seetaface2进行封装的JAVA...

  • spark-corenlp

    This package wraps Stanford CoreNLP annotators ...

  • capsnet-with-caps...

    CapsNet with capsule-wise convolution Project ...

  • inferno-boilerplate

    This is a very basic boilerplate example for pe...