BAYESIAN OPTIMIZATION OF HYPERPARAMETERS FOR RAINBOW DQN IN THE CARTPOLE-V1 ENVIRONMENT
ICTACT Journal on Data Science and Machine Learning · 01.03.2026 · 7 (2) · 990-995
DOI: 10.21917/ijdsml.2026.0188 ↗Kurz gefasst
Fachartikel in der Zeitschrift ICTACT Journal on Data Science and Machine Learning, online erschienen am 01.03.2026. Verfasst von Akhil Veluru. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
This paper presents a Bayesian optimization approach to hyperparameter tuning for the Rainbow DQN reinforcement learning algorithm, using the Hyperopt library and the CartPole-v1 environment as a benchmark. The study investigates the impact of search space definition on the convergence and quality of optimized hyperparameters. Further, it analyzes the effectiveness of different evaluation methods in the context of hyperparameter optimization for deep reinforcement learning. Results demonstrate the efficacy of Bayesian optimization in identifying high-performing hyperparameter configurations for Rainbow DQN in this control task.
Zitieren
APA
Veluru, A. (2026). BAYESIAN OPTIMIZATION OF HYPERPARAMETERS FOR RAINBOW DQN IN THE CARTPOLE-V1 ENVIRONMENT. ICTACT Journal on Data Science and Machine Learning, 7(2), 990-995. https://doi.org/10.21917/ijdsml.2026.0188
Vancouver
Veluru A. BAYESIAN OPTIMIZATION OF HYPERPARAMETERS FOR RAINBOW DQN IN THE CARTPOLE-V1 ENVIRONMENT. ICTACT Journal on Data Science and Machine Learning. 2026;7(2):990-995. doi:10.21917/ijdsml.2026.0188
BibTeX
@article{Veluru2026,
author = {Veluru, Akhil},
title = {BAYESIAN OPTIMIZATION OF HYPERPARAMETERS FOR RAINBOW DQN IN THE CARTPOLE-V1 ENVIRONMENT},
journal = {ICTACT Journal on Data Science and Machine Learning},
year = {2026},
volume = {7},
number = {2},
pages = {990--995},
doi = {10.21917/ijdsml.2026.0188}
}
EUVIMED