Skip to content

Latest commit

 

History

7 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

    Value Gradient Flow

Image

Installation

To install the full dependencies, simply run:

pip install -r requirements.txt

To use D4RL environments, you need to additionally set up MuJoCo 2.1.0.

Usage

Paper results can be reproduced by running ./run_scripts/run_vgf_off_d4rl.sh, ./run_scripts/run_vgf_off_ogbench.sh, ./run_scripts/run_vgf_off2on_ogbench.sh.

Wandb runs can be found at here

Acknowledgments

This codebase is built on top of fql's reference implementations.

About

[ICLR 2026] The official implementation of "Reinforcement Learning via Value Gradient Flow"

Resources

Stars

15 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages