loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Philipp Altmann ; Céline Davignon ; Maximilian Zorn ; Fabian Ritz ; Claudia Linnhoff-Popien and Thomas Gabor

Affiliation: LMU Munich, Germany

Keyword(s): Reinforcement Learning, Interpretability, Genetic Algorithms.

Abstract: To enhance the interpretability of Reinforcement Learning (RL), we propose Revealing Evolutionary Action Consequence Trajectories (REACT). In contrast to the prevalent practice of validating RL models based on their optimal behavior learned during training, we posit that considering a range of edge-case trajectories provides a more comprehensive understanding of their inherent behavior. To induce such scenarios, we introduce a disturbance to the initial state, optimizing it through an evolutionary algorithm to generate a diverse population of demonstrations. To evaluate the fitness of trajectories, REACT incorporates a joint fitness function that encourages local and global diversity in the encountered states and chosen actions. Through assessments with policies trained for varying durations in discrete and continuous environments, we demonstrate the descriptive power of REACT. Our results highlight its effectiveness in revealing nuanced aspects of RL models’ behavior beyond optimal performance, with up to 400% increased fidelities, contributing to improved interpretability. Code and videos are available at https://github.com/philippaltmann/REACT. (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 74.48.170.251

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:
Altmann, P., Davignon, C., Zorn, M., Ritz, F., Linnhoff-Popien, C. and Gabor, T. (2024). REACT: Revealing Evolutionary Action Consequence Trajectories for Interpretable Reinforcement Learning. In Proceedings of the 16th International Joint Conference on Computational Intelligence - ECTA; ISBN 978-989-758-721-4; ISSN 2184-3236, SciTePress, pages 127-138. DOI: 10.5220/0013005900003837

@conference{ecta24,
author={Philipp Altmann and Céline Davignon and Maximilian Zorn and Fabian Ritz and Claudia Linnhoff{-}Popien and Thomas Gabor},
title={REACT: Revealing Evolutionary Action Consequence Trajectories for Interpretable Reinforcement Learning},
booktitle={Proceedings of the 16th International Joint Conference on Computational Intelligence - ECTA},
year={2024},
pages={127-138},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013005900003837},
isbn={978-989-758-721-4},
issn={2184-3236},
}

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computational Intelligence - ECTA
TI - REACT: Revealing Evolutionary Action Consequence Trajectories for Interpretable Reinforcement Learning
SN - 978-989-758-721-4
IS - 2184-3236
AU - Altmann, P.
AU - Davignon, C.
AU - Zorn, M.
AU - Ritz, F.
AU - Linnhoff-Popien, C.
AU - Gabor, T.
PY - 2024
SP - 127
EP - 138
DO - 10.5220/0013005900003837
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: [email protected]

EXTERNAL LINKS

PRIMORIS

INSTICC

SCITEVENTS

CROSSREF

PROCEEDINGS SUBMITTED FOR INDEXATION BY:

dblp

Ei Compendex

SCOPUS

Semantic Scholar

Google Scholar

Microsoft Academic