Skip to Main content Skip to Navigation
New interface
Journal articles

Algorithmes de sortie du Piège de la Zone Ennuyeuse en apprentissage par renforcement

Abstract : Reinforcement learning algorithms have succeeded over the years in achieving impressive results in a variety of fields. However, these algorithms suffer from certain weaknesses highlighted by Refael Vivanti and al. that may explain the regression of even well-trained agents in certain environments : the difference in variance on rewards between areas of the environment. This difference in variance leads to two problems : Boring Area Trap and Manipulative consultant. We note that the Adaptive Symmetric Reward Noising (ASRN) algorithm proposed by Refael Vivanti and al. has limitations for environments with the following characteristics : long game times and multiple boring area environments. To overcome these problems, we propose three algorithms derived from the ASRN algorithm called Rebooted Adaptive Symmetric Reward Noising (RASRN) : Continuous ε decay RASRN, Full RASRN and Stepwise α decay RASRN. Thanks to two series of experiments carried out on the k-armed bandit problem, we show that our algorithms can better correct the Boring Area Trap problem.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-02925738
Contributor : Landry Steve Noulawe Tchamanbe Connect in order to contact the contributor
Submitted on : Friday, July 2, 2021 - 11:37:46 AM
Last modification on : Monday, October 10, 2022 - 12:34:07 PM

File

ARIMA-FR-Latex.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Landry Steve Noulawe Tchamanbe, Paulin Melatagia Yonta. Algorithmes de sortie du Piège de la Zone Ennuyeuse en apprentissage par renforcement. Revue Africaine de Recherche en Informatique et Mathématiques Appliquées, 2021, Volume 34 - 2020 - Special Issue CARI 2020 (CARI 2020), ⟨10.46298/arima.6748⟩. ⟨hal-02925738v3⟩

Share

Metrics

Record views

124

Files downloads

301