Source code for paper Classification with Costly Features using Deep Reinforcement Learning.
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
config_datasets
tools AAAI-2019 Nov 6, 2018
trained_hpc
.gitignore public release Jan 3, 2018
LICENSE public release Jan 3, 2018
README.md updated sources Feb 7, 2019
agent.py AAAI-2019 Nov 6, 2018
brain.py AAAI-2019 Nov 6, 2018
config.py
env.py AAAI-2019 Nov 6, 2018
eval.py
log.py AAAI-2019 Nov 6, 2018
main.py AAAI-2019 Nov 6, 2018
net.py
pool.py
utils.py AAAI-2019 Nov 6, 2018

README.md

This is a source code for AAAI 2019 paper Classification with Costly Features using Deep Reinforcement Learning wrote by Jaromír Janisch, Tomáš Pevný and Viliam Lisý: paper / slides / poster / code / blog

Cite as:

@inproceedings{janisch2019classification,
  title={Classification with Costly Features using Deep Reinforcement Learning},
  author={Janisch, Jaromír and Pevný, Tomáš and Lisý, Viliam},
  booktitle={AAAI Conference on Artificial Intelligence},
  year={2019}
}

Prerequisites:

  • cuda capable hardware
  • ubuntu 16.04
  • cuda 8/9
  • python 3.6 (numpy, pandas, pytorch 0.4)

Usage:

  • use tools tools/conv_*.py to prepare datasets; read the headers of those files; data is expected to be in ../data
  • pretrained HPC models are in trained_hpc, or you can use tools/hpc_svm.py to recreate them; they are needed in ../data
  • run python3.6 main.py --dataset [dataset] --flambda [lambda] --use_hpc [0|1] --pretrain [0|1], choose dataset from config_datasets/
  • the run will create multiple log files run*.dat
  • you can use octave or matlab to analyze them with tools/debug.m
  • you can also evaluate the agent on the test set with eval.py --dataset [dataset] --flambda [lambda]