Skip to content

Reinforcement learning on the Jaco Arm in Gazebo using Gym. An honours project at McGill University.

Notifications You must be signed in to change notification settings

aalexsmithh/jaco-gym

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

44 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

jaco-gym

This is a WIP package that will allow the Jaco arm Gazebo simulation to be incorporated into OpenAI Gym.

The video below shows an example of a TRPO agent playing cup-and-ball after about 5000 episodes.

Jaco Arm playing cup-and-ball

Running

$ cd run
$ python gym-testing.py

Requirements

This package has a number of dependencies, and the setup is non-trivial

Sources

  • Extending the OpenAI Gym for robotics: a toolkit for reinforcement learning using ROS and Gazebo 1608.05742

To look at

About

Reinforcement learning on the Jaco Arm in Gazebo using Gym. An honours project at McGill University.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published