Skip to content

Latest commit

 

History

History
16 lines (10 loc) · 833 Bytes

README.md

File metadata and controls

16 lines (10 loc) · 833 Bytes

Anti-Exploration with Distributional Random Network Distillation on PyTorch

This repository contains possible (not ideal one actually) PyTorch implementation of offline SAC DRND with the wandb integration. Actually, It is just a slightly modified my realization of SAC RND.

if you want to train the model, setup drnd_config in config.py, initialize SACDRNDTrainer in trainer.py and run its train method:

from trainer import SACDRNDTrainer

trainer = SACDRNDTrainer()
trainer.train()

if you find any bugs and mistakes in the code, please contact me :)