All Projects → donghaiwang → AI

donghaiwang / AI

Licence: MIT license
使用深度强化学习解决视觉跟踪和视觉导航问题

Programming Languages

matlab
3953 projects
python
139335 projects - #7 most used programming language
java
68154 projects - #9 most used programming language
shell
77523 projects
c
50402 projects - #5 most used programming language
Batchfile
5799 projects

Projects that are alternatives of or similar to AI

Neural Slam
Pytorch code for ICLR-20 Paper "Learning to Explore using Active Neural SLAM"
Stars: ✭ 414 (+2487.5%)
Mutual labels:  navigation, deep-reinforcement-learning
Object-Goal-Navigation
Pytorch code for NeurIPS-20 Paper "Object Goal Navigation using Goal-Oriented Semantic Exploration"
Stars: ✭ 107 (+568.75%)
Mutual labels:  navigation, deep-reinforcement-learning
DDPG
End to End Mobile Robot Navigation using DDPG (Continuous Control with Deep Reinforcement Learning) based on Tensorflow + Gazebo
Stars: ✭ 41 (+156.25%)
Mutual labels:  navigation, deep-reinforcement-learning
motion-planner-reinforcement-learning
End to end motion planner using Deep Deterministic Policy Gradient (DDPG) in gazebo
Stars: ✭ 99 (+518.75%)
Mutual labels:  navigation, deep-reinforcement-learning
LWDRLC
Lightweight deep RL Libraray for continuous control.
Stars: ✭ 14 (-12.5%)
Mutual labels:  deep-reinforcement-learning
chi
A high-level framework for advanced deep learning with TensorFlow
Stars: ✭ 55 (+243.75%)
Mutual labels:  deep-reinforcement-learning
navigation array
Helper function for building navigations for REDAXO cms
Stars: ✭ 22 (+37.5%)
Mutual labels:  navigation
TF RL
Eagerly Experimentable!!!
Stars: ✭ 22 (+37.5%)
Mutual labels:  deep-reinforcement-learning
Meta-Learning-for-StarCraft-II-Minigames
We reproduced DeepMind's results and implement a meta-learning (MLSH) agent which can generalize across minigames.
Stars: ✭ 26 (+62.5%)
Mutual labels:  deep-reinforcement-learning
drift drl
High-speed Autonomous Drifting with Deep Reinforcement Learning
Stars: ✭ 82 (+412.5%)
Mutual labels:  deep-reinforcement-learning
navdatareader
Navdatareader is a command line tool that uses the atools fs/bgl and fs/writer to store a full flight simulator scenery database into a relational database like Sqlite or MySql.
Stars: ✭ 35 (+118.75%)
Mutual labels:  navigation
vox nav
A project to develop/adapt a navigation system for outdoor robotics in rough uneven terrains
Stars: ✭ 101 (+531.25%)
Mutual labels:  navigation
multi view ram
No description or website provided.
Stars: ✭ 26 (+62.5%)
Mutual labels:  deep-reinforcement-learning
deep-rts
A Real-Time-Strategy game for Deep Learning research
Stars: ✭ 152 (+850%)
Mutual labels:  deep-reinforcement-learning
imitation learning
PyTorch implementation of some reinforcement learning algorithms: A2C, PPO, Behavioral Cloning from Observation (BCO), GAIL.
Stars: ✭ 93 (+481.25%)
Mutual labels:  deep-reinforcement-learning
bottom-nav
Material Design bottom-nav https://material.io/guidelines/components/bottom-navigation.html
Stars: ✭ 25 (+56.25%)
Mutual labels:  navigation
godot 2d navmesh generator
Godot plugin that generates a 2D navigation mesh from collsion nodes.
Stars: ✭ 35 (+118.75%)
Mutual labels:  navigation
easyRNRoute
https://medium.com/@kevinle/comprehensive-routing-and-navigation-in-react-native-made-easy-6383e6cdc293#.nttfeeq3p
Stars: ✭ 25 (+56.25%)
Mutual labels:  navigation
jquery-scrollwatch
jQuery plugin for determining active sections on the page based on scrolling
Stars: ✭ 18 (+12.5%)
Mutual labels:  navigation
diractions
👨‍💻 Doing Anything, Anywhere, from Here [zsh] 🚏
Stars: ✭ 30 (+87.5%)
Mutual labels:  navigation

人工智能

研究领域包括计算机视觉、生物视觉、自动驾驶的工具。

入门

深度学习、深度强化学习,具体子问题包括视觉目标跟踪和平稳跟踪的相关性、多目标跟踪等。

环境

开发测试平台Ubuntu 18.04、Windows 10。

Matlab 2018a
Python 3.6

安装

所有安装包下载地址

Matlab 2018a

Matlab 2018a(包括Windows、Linux、Mac平台的安装包及安装步骤)

Python

Python 3.6.5(Anaconda3-5.2.0)
添加环境变量:C:\Users\dong\Anaconda3
			 C:\Users\dong\Anaconda3\Scripts
pip install opencv_python-3.4.2-cp36-cp36m-win_amd64.whl
pip install -i https://pypi.tuna.tsinghua.edu.cn/simple tqdm
pip install -i https://pypi.tuna.tsinghua.edu.cn/simple gym==0.7.0
pip install --no-index -f https://github.com/Kojoley/atari-py/releases atari_py
pip install -i https://pypi.tuna.tsinghua.edu.cn/simple tensorflow-gpu==1.4.0
git clone https://github.com/donghaiwang/AI.git
  • 安装CUDA8.0:配置PATH路径,C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v8.0 (另外包括v8.0\bin、v8.0\lib\x64、v8.0\libnvvp)。

  • 安装cuDNN6:将压缩包里的bin、include、bin文件间拷贝到CUDA8.0安装的对应目录。

  • 安装pycharm-professional-2017.3 C:\Windows\System32\Drivers\etc\hosts 添加 0.0.0.0 account.jetbrains.com 激活码

尽量不依赖平台以外的库(依赖将会列出安装步骤)。

测试

实现训练、测试、latex编译自动化。

分解为自动化测试

测试的目的和内容

test

代码风格检查

为了更好的阅读,采用中文注释,能保证由代码能生成文档。

doc generate

构建

构建类型 状态
Linux CPU Status
Linux GPU Status
Windows CPU Status
Windows GPU Status

构建工具

贡献

欢迎热爱人工智能的仁人志士贡献代码,共同推动人工智能的进步。

作者

增加 作者列表 列出贡献的作者。

协议

遵守MIT协议,这意味着:

  • 你可以自由使用,复制,修改,可以用于自己的项目。
  • 可以免费分发或用来盈利。
  • 唯一的限制是必须包含许可声明。

鸣谢

  • Richard S. Sutton
  • etc
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].