ADDQ: adaptive distributional double Q-learning


Döring, Leif ; Wille, Benedikt ; Birr, Maximilian ; Bîrsan, Mihail ; Slowik, Martin


[img]
Preview
PDF
doring25a.pdf - Published

Download (12MB)

URL: https://proceedings.mlr.press/v267/doring25a.html
URN: urn:nbn:de:bsz:180-madoc-719430
Document Type: Conference or workshop publication
Year of publication: 2025
Book title: Proceedings of the 42nd International Conference on Machine Learning, PMLR
The title of a journal, publication series: Proceedings of Machine Learning Research : PMLR
Volume: 267
Page range: 14344-14390
Conference title: International Conference on Machine Learning
Location of the conference venue: Vancouver, Canada
Date of the conference: 13.-19.07.2025
Publisher: Singh, Aarti ; Fazel, Maryam ; Hsu, Daniel ; Lacoste-Julien, Simon ; Berkenkamp, Felix ; Maharaj, Tegan ; Wagstaff, Kiri ; Zhu, Jerry
Place of publication: Red Hook, NY
Publishing house: Curran Associates, Inc.
ISSN: 2640-3498
Related URLs:
Publication language: English
Institution: School of Business Informatics and Mathematics > Stochastics (Junioprofessur) (Slowik 2021-)
Subject: 004 Computer science, internet
Abstract: Bias problems in the estimation of Q-values are a well-known obstacle that slows down convergence of Q-learning and actor-critic methods. One of the reasons of the success of modern RL algorithms is partially a direct or indirect overestimation reduction mechanism. We introduce an easy to implement method built on top of distributional reinforcement learning (DRL) algorithms to deal with the overestimation in a locally adaptive way. Our framework ADDQ is simple to implement, existing DRL implementations can be improved with a few lines of code. We provide theoretical backup and experimental results in tabular, Atari, and MuJoCo environments, comparisons with state-of-the-art methods, and a proof of convergence in the tabular case.




Dieser Eintrag ist Teil der Universitätsbibliographie.

Das Dokument wird vom Publikationsserver der Universitätsbibliothek Mannheim bereitgestellt.




Metadata export


Citation


+ Search Authors in

+ Download Statistics

Downloads per month over past year

View more statistics



You have found an error? Please let us know about your desired correction here: E-Mail


Actions (login required)

Show item Show item