Dissecting Discrete Soft Actor-Critic: Limitations and Principled Alternatives

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Asad, Reza, Babanezhad, Reza, Vaswani, Sharan
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910209612447744
author Asad, Reza
Babanezhad, Reza
Vaswani, Sharan
author_facet Asad, Reza
Babanezhad, Reza
Vaswani, Sharan
contents While Soft Actor-Critic (SAC) is highly effective in continuous control, its discrete counterpart (DSAC) performs poorly on challenging discrete-action domains such as Atari. Consequently, starting from DSAC, we revisit the design of actor-critic methods in this setting. First, we determine that the coupling between the actor and critic entropy is the primary reason behind the poor performance of DSAC. We demonstrate that by merely decoupling these components, DSAC's performance significantly improves. Motivated by this insight, we introduce a flexible off-policy actor-critic framework that subsumes DSAC as a special case and yields novel objectives. Our framework allows using an m-step Bellman operator for the critic update, and instantiates the actor objective by combining standard policy optimization methods with entropy regularization. Theoretically, we prove that the proposed methods can guarantee convergence to the optimal regularized value function in the tabular setting, generalizing the results in prior work. Empirically, we evaluate the proposed objectives on standard Atari games. Our ablations indicate that, unlike DSAC, these objectives, including novel ones, perform robustly even without entropy regularization or explicit exploration mechanisms.
format Preprint
id arxiv_https___arxiv_org_abs_2509_09838
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Dissecting Discrete Soft Actor-Critic: Limitations and Principled Alternatives
Asad, Reza
Babanezhad, Reza
Vaswani, Sharan
Machine Learning
Artificial Intelligence
While Soft Actor-Critic (SAC) is highly effective in continuous control, its discrete counterpart (DSAC) performs poorly on challenging discrete-action domains such as Atari. Consequently, starting from DSAC, we revisit the design of actor-critic methods in this setting. First, we determine that the coupling between the actor and critic entropy is the primary reason behind the poor performance of DSAC. We demonstrate that by merely decoupling these components, DSAC's performance significantly improves. Motivated by this insight, we introduce a flexible off-policy actor-critic framework that subsumes DSAC as a special case and yields novel objectives. Our framework allows using an m-step Bellman operator for the critic update, and instantiates the actor objective by combining standard policy optimization methods with entropy regularization. Theoretically, we prove that the proposed methods can guarantee convergence to the optimal regularized value function in the tabular setting, generalizing the results in prior work. Empirically, we evaluate the proposed objectives on standard Atari games. Our ablations indicate that, unlike DSAC, these objectives, including novel ones, perform robustly even without entropy regularization or explicit exploration mechanisms.
title Dissecting Discrete Soft Actor-Critic: Limitations and Principled Alternatives
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2509.09838