On the consistency of hyper-parameter selection in value-based deep reinforcement learning
; 3:1037−1059, 2024.
Presented at the Reinforcement Learning Conference (RLC), Amherst Massachusetts, August 9–12, 2024.
Abstract
Deep reinforcement learning (deep RL) has achieved tremendous success on various domains through a combination of algorithmic design and careful selection of hyper-parameters. Algorithmic improvements are often the result of iterative enhancements built upon prior approaches, while hyper-parameter choices are typically inherited from previous methods or fine-tuned specifically for the proposed technique. Despite their crucial impact on performance, hyper-parameter choices are frequently overshadowed by algorithmic advancements. This paper conducts an extensive empirical study focusing on the reliability of hyper-parameter selection for value-based deep reinforcement learning agents. Our findings not only help establish which hyper-parameters are most critical to tune, but also help clarify which tunings remain consistent across different training regimes.
BibTeX
@article{ceron2024consistency,
title={On the consistency of hyper-parameter selection in value-based deep reinforcement learning},
author={Ceron, Johan Samir Obando and Ara{\'{u}}jo, Jo{\~{a}}o Guilherme Madeira and Courville, Aaron and Castro, Pablo Samuel},
journal={Reinforcement Learning Journal},
volume={3},
pages={1037--1059},
year={2024}
}