On the consistency of hyper-parameter selection in value-based deep reinforcement learning

Johan Samir Obando Ceron, João Guilherme Madeira Araújo, Aaron Courville, Pablo Samuel Castro

Keywords: Deep reinforcement learning, hyperparameters

TL;DR: We conduct an extensive empirical study focusing on the reliability of hyper-parameter selection for value-based deep reinforcement learning agents

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.

Submission Number: 128