Skip to content

Pytorch Implementation for First Order Constrained Optimization in Policy Space (FOCOPS).

Notifications You must be signed in to change notification settings

Ali-Razmdideh/focops

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Implementation for First Order Constrained Optimization in Policy Space (FOCOPS).

Link to paper https://arxiv.org/abs/2002.06506

Requirements

python (tested on 3.6.8)
pytorch (tested on 1.3.1)
gym (tested on 0.15.3)
MuJoCo v2.0
mujoco-py (tested on 1.50.1.0)
For the circle experiments, please also install circle environments at https://github.com/ymzhang01/mujoco-circle.

Implementation

Example: Humanoid task in the robots with speed limits experiments (using the default parameters)

python focops_main.py --env-id='Humanoid-v3' --constraint='velocity'

About

Pytorch Implementation for First Order Constrained Optimization in Policy Space (FOCOPS).

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%