Skip to content

This is the source code of the paper "Demonstration-Guided Continual Reinforcement Learning in Dynamic Environments"

Notifications You must be signed in to change notification settings

XueYang0130/DGCRL

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 

Repository files navigation

Overview

Dependencies

The dependencies for this repository is in MAPI.yml

Train

Run DG_train.py to train the DGCRL mdoel

Take Hopper train as an example, run DG_train.py with the parameter as --env hopper -- curve_mode normal --demo_num 50 and --reset_mode a_c

Demonstrations

The initial guidance demonstrations are stored in DGCRL/train/rand_demo

Task Info

The task info is shown in task_info repository.

About

This is the source code of the paper "Demonstration-Guided Continual Reinforcement Learning in Dynamic Environments"

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages