Code Monkey home page Code Monkey logo

bnd-ddqn's Introduction

BND-DDQN

The tensorflow implmentation of paper: Learn to Steer through Deep Reinforcement Learning

Videos of our experiments are available at Video1 and Video2.

Prerequisites

Python 3.5
Tensorflow 1.13.1
ROS Kinetic

Instruction

Clone the pioneer_utils folder to your catkin workspace and catkin_make:

cd ~/catkin_ws/
catkin_make
source ~/catkin_ws/devel/setup.bash

Launch the simulator with command:

roslaunch pioneer_utils p3_world.launch

Start training with command:

python main.py

Citation

If you find this method useful in your research, please cite:

@article{wu2018learn,
  title={Learn to steer through deep reinforcement learning},
  author={Wu, Keyu and Abolfazli Esfahani, Mahdi and Yuan, Shenghai and Wang, Han},
  journal={Sensors},
  volume={18},
  number={11},
  pages={3650},
  year={2018},
  publisher={Multidisciplinary Digital Publishing Institute}
}

bnd-ddqn's People

Contributors

kerrywu16 avatar

Stargazers

Elvis Rodrigues avatar  avatar Kemal Bektas avatar Tianfu Wang avatar  avatar

Watchers

James Cloos avatar  avatar paper2code - bot avatar

Forkers

braveheart0215

bnd-ddqn's Issues

run error

Thanks for your great work!

I'm facing a problem when I run roslaunch pioneer_utils p3_world.launch

  1. My python is 3.5
  2. Tensorflow is 1.13.1
  3. ROS Kinetic
  4. When I run roslaunch pioneer_utils p3_world.launch in the terminal
    The error showed in terminal is:
    Traceback (most recent call last):
    File "/opt/ros/kinetic/share/xacro/xacro.py", line 55, in
    import xacro
    File "/opt/ros/kinetic/lib/python2.7/dist-packages/xacro/init.py", line 35, in
    import glob
    File "/usr/lib/python3.5/glob.py", line 4, in
    import re
    ImportError: No module named 're'
  5. I think the version of python cause this problem. However, after I change to python2.7 + ensorflow is 1.13.1 + ROS Kinetic.
    5.1 The problem is:
    When I run roslaunch pioneer_utils p3_world.launch in the first terminal,
    some ROS INFO showed in the terminal:
    SpawnModel script started
    [ INFO] [1579333142.286742338]: Finished loading Gazebo ROS API Plugin.
    [ INFO] [1579333142.287142658]: waitForService: Service [/gazebo/set_physics_properties] has not been advertised, waiting...
    [ INFO] [1579333142.317293071]: Finished loading Gazebo ROS API Plugin.
    [ INFO] [1579333142.317689942]: waitForService: Service [/gazebo/set_physics_properties] has not been advertised, waiting...
    [INFO] [1579333142.326618, 0.000000]: Loading model XML from ros parameter
    [INFO] [1579333142.328966, 0.000000]: Waiting for service /gazebo/spawn_urdf_model
    [INFO] [1579333145.353341, 0.000000]: Calling service /gazebo/spawn_urdf_model

5.2 When I run python main.py, nothing happened. Nothing run in the Gazebo.

Can you give me some suggestions to solve this problem?
Thanks a lot!

how to ensure the trained models are transferable from simulation to reality

Hi, I am a beginner in reinforcement learning. Thank you for sharing your paper, it has helped me a lot. I recently tried to port a model trained in gazebo to a real mobile bot. The robot has no problem subscribing and posting topics, but the robot is spinning in place, hesitating and unable to move forward. I wonder if this is caused by the difference between the simulation and the real environment, so I would like to ask you if you have encountered similar problems or if you know how to solve this?

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.