Skip to content

kuds/rl-fetch

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

57 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Fetch Mobile Manipulator

Fetch Push

image

Fetch Slide

image

Fetch Pick and Place

image

Fetch Reach

image

Results

Hardware: Google Colab L4

Environment Model Type Average Reward Total Training Steps HuggingFace
Reach TQC -0.59 1,000,000 Link
Reach DDPG -0.65 1,000,000 Link
Push TQC -2.02 1,000,000 Link
Slide TQC -6.65 1,000,000 Link
Pick and Place TQC -2.07 1,000,000 Link
Pick and Place DDPG -11.01 1,000,000 Link

Training Notes

  • Set learning_starts needs to be greater than 100 as the Fetch environment are defaulted to end at 50 steps (max_episode_steps=50) and this will cause for TQC
  • Due to overestimation issues with DDPG, it will struggle in more complex environment like in Pick & Place and Slide. So it is excepted for DDPG struggle to "solve" the Fetch environments

Finding Theta Blog Posts

About

No description or website provided.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors