Saved in:
Bibliographic Details
Main Authors: Neo, Dexter, Chen, Tsuhan
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2310.17173
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918066910134272
author Neo, Dexter
Chen, Tsuhan
author_facet Neo, Dexter
Chen, Tsuhan
contents We present a novel extension to the family of Soft Actor-Critic (SAC) algorithms. We argue that based on the Maximum Entropy Principle, discrete SAC can be further improved via additional statistical constraints derived from a surrogate critic policy. Furthermore, our findings suggests that these constraints provide an added robustness against potential domain shifts, which are essential for safe deployment of reinforcement learning agents in the real-world. We provide theoretical analysis and show empirical results on low data regimes for both in-distribution and out-of-distribution variants of Atari 2600 games.
format Preprint
id arxiv_https___arxiv_org_abs_2310_17173
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle DSAC-C: Constrained Maximum Entropy for Robust Discrete Soft-Actor Critic
Neo, Dexter
Chen, Tsuhan
Machine Learning
We present a novel extension to the family of Soft Actor-Critic (SAC) algorithms. We argue that based on the Maximum Entropy Principle, discrete SAC can be further improved via additional statistical constraints derived from a surrogate critic policy. Furthermore, our findings suggests that these constraints provide an added robustness against potential domain shifts, which are essential for safe deployment of reinforcement learning agents in the real-world. We provide theoretical analysis and show empirical results on low data regimes for both in-distribution and out-of-distribution variants of Atari 2600 games.
title DSAC-C: Constrained Maximum Entropy for Robust Discrete Soft-Actor Critic
topic Machine Learning
url https://arxiv.org/abs/2310.17173