Skip to content

SiyuanLee/HESS

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Active Hierarchical Exploration with Stable Subgoal Representation Learning

Prerequisites

Running Experiments

We provide the scripts for training and evaluation in ./scripts/near_goal.sh.

The parameter setting can be found in ./arguments.

Training Example

python train_hier_sac.py --c 50 --abs_range 20  --env-name AntMaze1Test-v1 --test AntMaze1Test-v1 --weight_decay 1e-5 --device cuda:0 --seed 2

Evaluating Example

python train_hier_sac.py --c 50 --abs_range 20  --test AntMaze1Test-v1 --resume True --eval True --weight_decay 1e-5  --device cuda:0 --seed 124  --animate True

You also need to specify the location of saved models in the resume-path argument.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors