Skip to content
/ aop Public

Official codebase for Adaptive Online Planning for Continual Lifelong Learning.

Notifications You must be signed in to change notification settings

kzl/aop

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Adaptive Online Planning

Associated code for our paper, Adaptive Online Planning for Continual Lifelong Learning. See our website for more details.

Requirements

  1. Clone/download a copy of this repository.
  2. Code uses Python 3, as well as the following packages, which can be installed via pip/conda: numpy, gym, scipy, torch, matplotlib, and seaborn.
  3. Install MuJoCo and mujoco-py.

Running Experiments

To run an experiment, run the command (all args are optional, use -h for help/more information):

python run.py --a aop -e hopper -s changing

Visualizing Experiments

To visualize results, identify the directory of the experiment and run (replace ex/1124_1200 with relevant directory and 20000 with the length of the experiment):

python graph.py ex/1124_1200 20000

About

Official codebase for Adaptive Online Planning for Continual Lifelong Learning.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages