loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Wenzel Baron Pilar von Pilchau 1 ; Anthony Stein 2 and Jörg Hähner 1

Affiliations: 1 Organic Computing Group, University of Augsburg, Eichleitnerstr. 30, Augsburg, Germany ; 2 Artificial Intelligence in Agricultural Engineering, University of Hohenheim, Garbenstraße 9, Hohnheim, Germany

Keyword(s): Experience Replay, Deep Q-Network, Deep Reinforcement Learning, Interpolation, Machine Learning.

Abstract: An important component of many Deep Reinforcement Learning algorithms is the Experience Replay that serves as a storage mechanism or memory of experienced transitions. These experiences are used for training and help the agent to stably find the perfect trajectory through the problem space. The classic Experience Replay however makes only use of the experiences it actually made, but the stored transitions bear great potential in form of knowledge about the problem that can be extracted. The gathered knowledge contains state-transitions and received rewards that can be utilized to approximate a model of the environment. We present an algorithm that creates synthetic experiences in a nondeterministic discrete environment to assist the learner with augmented training data. The Interpolated Experience Replay is evaluated on the FrozenLake environment and we show that it can achieve a 17% increased mean reward compared to the classic version.

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.238.82.77

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
von Pilchau, W.; Stein, A. and Hähner, J. (2020). Bootstrapping a DQN Replay Memory with Synthetic Experiences. In Proceedings of the 12th International Joint Conference on Computational Intelligence (IJCCI 2020) - NCTA; ISBN 978-989-758-475-6; ISSN 2184-3236, SciTePress, pages 404-411. DOI: 10.5220/0010107904040411

@conference{ncta20,
author={Wenzel Baron Pilar {von Pilchau}. and Anthony Stein. and Jörg Hähner.},
title={Bootstrapping a DQN Replay Memory with Synthetic Experiences},
booktitle={Proceedings of the 12th International Joint Conference on Computational Intelligence (IJCCI 2020) - NCTA},
year={2020},
pages={404-411},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010107904040411},
isbn={978-989-758-475-6},
issn={2184-3236},
}

TY - CONF

JO - Proceedings of the 12th International Joint Conference on Computational Intelligence (IJCCI 2020) - NCTA
TI - Bootstrapping a DQN Replay Memory with Synthetic Experiences
SN - 978-989-758-475-6
IS - 2184-3236
AU - von Pilchau, W.
AU - Stein, A.
AU - Hähner, J.
PY - 2020
SP - 404
EP - 411
DO - 10.5220/0010107904040411
PB - SciTePress