Skip to content

bileldeb/Hindsight-Goal-Generation

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

15 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Hindsight Goal Generation (HGG)

HGG fork to enable hgg on a pybullet mobile manipulator

Requirements

conda create -n hggenv python = 3.7

conda activate hggenv

pip install tensorflow==1.15

pip install protobuf==3.20.0

pip install BeautifulTable==0.7.0

pip install path/to/pandagym

Running Commands

default env PandaMobilePickAndPlace-v3

episodes the number of hindsight goals

python train.py  
python train.py  --env=PandaReach-v3
python train.py  --env=PandaMobileReach-v3 --episodes=15 --timesteps=300

About

An HGG Fork to train a mobile manipulator

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 97.3%
  • C 2.7%