Skip to content

JL321/PolicyGradients-torch

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

19 Commits
 
 
 
 

Repository files navigation

PolicyGradients-torch

This repo contains implementations of SAC and DDPG in pytorch.

Dependencies:

  • gym
  • numpy
  • pytorch (scripts written in cuda 9.2)
  • python3

Structure:

  • train.py is the main file to be run: use --test to load a model, and run the model for evaluation
  • Hyperparameters are set by default, and are located in the train.py model
  • util.py contains the experience buffer
  • SAC.py and DDPG.py are self contained classes that include all content pertained to both algorithms
  • SAC and DDPG can be interchangably loaded by changing the model imported in train.py

Additional guidelines to be added

About

Policy Gradient implementations in pytorch

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages