BOOK: Storing Algorithm-Invariant Episodes for Deep Reinforcement Learning

Simyung Chang, YoungJoon Yoo, Jaeseok Choi, Nojun Kwak

2019

Abstract

We introduce a novel method to train agents of reinforcement learning (RL) by sharing knowledge in a way similar to the concept of using a book. The recorded information in the form of a book is the main means by which humans learn knowledge. Nevertheless, the conventional deep RL methods have mainly focused either on experiential learning where the agent learns through interactions with the environment from the start or on imitation learning that tries to mimic the teacher. Contrary to these, our proposed book learning shares key information among different agents in a book-like manner by delving into the following two characteristic features: (1) By defining the linguistic function, input states can be clustered semantically into a relatively small number of core clusters, which are forwarded to other RL agents in a prescribed manner. (2) By defining state priorities and the contents for recording, core experiences can be selected and stored in a small container. We call this container as ‘BOOK’. Our method learns hundreds to thousand times faster than the conventional methods by learning only a handful of core cluster information, which shows that deep RL agents can effectively learn through the shared knowledge from other agents.

Download


Paper Citation


in Harvard Style

Chang S., Yoo Y., Choi J. and Kwak N. (2019). BOOK: Storing Algorithm-Invariant Episodes for Deep Reinforcement Learning.In Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-351-3, pages 73-82. DOI: 10.5220/0007308000730082


in Bibtex Style

@conference{icpram19,
author={Simyung Chang and YoungJoon Yoo and Jaeseok Choi and Nojun Kwak},
title={BOOK: Storing Algorithm-Invariant Episodes for Deep Reinforcement Learning},
booktitle={Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2019},
pages={73-82},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007308000730082},
isbn={978-989-758-351-3},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - BOOK: Storing Algorithm-Invariant Episodes for Deep Reinforcement Learning
SN - 978-989-758-351-3
AU - Chang S.
AU - Yoo Y.
AU - Choi J.
AU - Kwak N.
PY - 2019
SP - 73
EP - 82
DO - 10.5220/0007308000730082