Skip to content

Solving ceetah,cartpole,reacher,walker Deepmind Control Suite using DDPG (Pythorc)

Notifications You must be signed in to change notification settings

DrLux/DDPG_on_DMControl_Suite

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

DDPG_on_DMControl_Suite

Solving cheetah,cartpole,reacher,walker Deepmind Control Suite using DDPG

This repo is from my Master's degree thesis work. I used PlaNet to prove that model-based DRL can overcome the model-free algorithms in terms of sample efficiency. I extended the MoritzTaylor implementation to make it compatible with the Deepmind Control Suite.

To have more details on the full work, visit blog article.

Results


ceetah_planet_vs_ddpg cartpole_planet_vs_ddpg reacher_planet_vs_ddpg walker_planet_vs_ddpg

Links


My work with PlaNet MoritzTaylor implementation OpenAi implementation

Releases

No releases published

Packages

No packages published

Languages