Skip to content
/ pytorch-ddpg-naf Public

Implementation of algorithms for continuous control (DDPG and NAF).

License

MIT license
304 stars 72 forks Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

ikostrikov/pytorch-ddpg-naf

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

35 Commits

LICENSE.md

LICENSE.md

 
 

README.md

README.md

 
 

ddpg.py

ddpg.py

 
 

main.py

main.py

 
 

naf.py

naf.py

 
 

normalized_actions.py

normalized_actions.py

 
 

ounoise.py

ounoise.py

 
 

param_noise.py

param_noise.py

 
 

replay_memory.py

replay_memory.py

 
 

Repository files navigation

DEPRECATION

This repository is deprecated and is no longer maintaned. Please see a more recent implementation of RL for continuous control at jax-sac.

Description

Reimplementation of Continuous Deep Q-Learning with Model-based Acceleration and Continuous control with deep reinforcement learning.

Contributions are welcome. If you know how to make it more stable, don't hesitate to send a pull request.

Run

Use the default hyperparameters.

For NAF:

python main.py --algo NAF --env-name HalfCheetah-v2

For DDPG

python main.py --algo DDPG --env-name HalfCheetah-v2

About

Implementation of algorithms for continuous control (DDPG and NAF).

Topics

reinforcement-learning deep-learning pytorch ddpg deep-deterministic-policy-gradient

Resources

Readme

License

MIT license
Activity

Stars

304 stars

Watchers

10 watching

Forks

72 forks
Report repository

Releases

No releases published

Packages

No packages published

Contributors 4

  •  
  •  
  •  
  •  

Languages