GitHub

This repo is for the paper: Theory-inspired Parameter Control Benchmarks for Dynamic Algorithm Configuration

The DAC environment is based on the Dynamic Algorithm Configuration benchmark library DACBench.

For computing the optimal DAC policy for RLS (Randomized Local Search) on LeadingOne problem, please check the instructions in rls_lo/optimal_policy/.

For training/evaluating a DDQN agent on this benchmark, please see the instructions in rls_lo/rl.

Name		Name	Last commit message	Last commit date
Latest commit History 4 Commits
DACBench.egg-info		DACBench.egg-info
dacbench		dacbench
docs		docs
examples		examples
rls_lo		rls_lo
runscripts		runscripts
tests		tests
Getting started.ipynb		Getting started.ipynb
LICENSE		LICENSE
README.md		README.md
README_DACBench.md		README_DACBench.md
log_jupyter		log_jupyter
pyproject.toml		pyproject.toml
run.py		run.py
run_ppo.sh		run_ppo.sh
setup.cfg		setup.cfg
setup.py		setup.py
start.sh		start.sh
train_ppo.py		train_ppo.py

License

CarolaDoerr/LeadingOneDAC

Folders and files

Latest commit

History

Repository files navigation

About

Resources

License

Stars

Watchers

Forks

Languages