loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Roman Liessner 1 ; Jan Dohmen 1 and Marco Wiering 2

Affiliations: 1 Dresden Institute of Automobile Engineering, TU Dresden, George-Bähr-Straße 1, Dresden, Germany ; 2 Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, 9747 AG Groningen, The Netherlands

Keyword(s): Reinforcement Learning, Explainable AI, Longitudinal Control, SHAP.

Abstract: Deep Reinforcement Learning (DRL) has the potential to surpass the existing state of the art in various practical applications. However, as long as learned strategies and performed decisions are difficult to interpret, DRL will not find its way into safety-relevant fields of application. SHAP values are an approach to overcome this problem. It is expected that the addition of these values to DRL provides an improved understanding of the learned action-selection policy. In this paper, the application of a SHAP method for DRL is demonstrated by means of the OpenAI Gym LongiControl Environment. In this problem, the agent drives an autonomous vehicle under consideration of speed limits in a single lane route. The controls learned with a DDPG algorithm are interpreted by a novel approach combining learned actions and SHAP values. The proposed RL-SHAP representation makes it possible to observe in every time step which features have a positive or negative effect on the selected action and which influences are negligible. The results show that RL-SHAP values are a suitable approach to interpret the decisions of the agent. (More)

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 3.128.79.88

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:
Liessner, R.; Dohmen, J. and Wiering, M. (2021). Explainable Reinforcement Learning for Longitudinal Control. In Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART; ISBN 978-989-758-484-8; ISSN 2184-433X, SciTePress, pages 874-881. DOI: 10.5220/0010256208740881

@conference{icaart21,
author={Roman Liessner. and Jan Dohmen. and Marco Wiering.},
title={Explainable Reinforcement Learning for Longitudinal Control},
booktitle={Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART},
year={2021},
pages={874-881},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010256208740881},
isbn={978-989-758-484-8},
issn={2184-433X},
}

TY - CONF

JO - Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART
TI - Explainable Reinforcement Learning for Longitudinal Control
SN - 978-989-758-484-8
IS - 2184-433X
AU - Liessner, R.
AU - Dohmen, J.
AU - Wiering, M.
PY - 2021
SP - 874
EP - 881
DO - 10.5220/0010256208740881
PB - SciTePress

- Science and Technology Publications, Lda.
RESOURCES

Proceedings

Papers

Authors

Ontology

CONTACTS

Science and Technology Publications, Lda
Avenida de S. Francisco Xavier, Lote 7 Cv. C,
2900-616 Setúbal, Portugal.

Phone: +351 265 520 185 (National fixed network call)
Fax: +351 265 520 186
Email: info@scitepress.org

EXTERNAL LINKS

PRIMORIS

INSTICC

SCITEVENTS

CROSSREF

PROCEEDINGS SUBMITTED FOR INDEXATION BY:

dblp

Ei Compendex

SCOPUS

Semantic Scholar

Google Scholar

Microsoft Academic