Saved in:
Bibliographic Details
Main Authors: Wang, Tongxi, Xia, Zhuoyang, Chen, Xinran, Liu, Shan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.19624
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909048098521088
author Wang, Tongxi
Xia, Zhuoyang
Chen, Xinran
Liu, Shan
author_facet Wang, Tongxi
Xia, Zhuoyang
Chen, Xinran
Liu, Shan
contents Real-world reinforcement learning often faces environment drift, but most existing methods rely on static entropy coefficients/target entropy, causing over-exploration during stable periods and under-exploration after drift, and leaving unanswered the principled question of how exploration intensity should scale with drift magnitude. We show that, under standard assumptions, entropy scheduling in non-stationary maximum-entropy RL can be cast as the dynamic-regret trade-off between tracking a drifting comparator and stabilizing updates, yielding a square-root scaling rule for the entropy weight in terms of a online non-stationarity proxy. Building on this, we propose AES--Adaptive Entropy Scheduling--which adaptively adjusts the entropy coefficient/temperature online using observable drift proxies during training, requiring almost no structural changes and incurring minimal overhead. Across 4 algorithm variants, 12 tasks, and 4 drift modes, AES significantly reduces the fraction of performance degradation caused by drift and accelerates recovery after abrupt changes.
format Preprint
id arxiv_https___arxiv_org_abs_2601_19624
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Tracking Drift: Variation-Aware Entropy Scheduling for Non-Stationary Reinforcement Learning
Wang, Tongxi
Xia, Zhuoyang
Chen, Xinran
Liu, Shan
Machine Learning
Artificial Intelligence
Real-world reinforcement learning often faces environment drift, but most existing methods rely on static entropy coefficients/target entropy, causing over-exploration during stable periods and under-exploration after drift, and leaving unanswered the principled question of how exploration intensity should scale with drift magnitude. We show that, under standard assumptions, entropy scheduling in non-stationary maximum-entropy RL can be cast as the dynamic-regret trade-off between tracking a drifting comparator and stabilizing updates, yielding a square-root scaling rule for the entropy weight in terms of a online non-stationarity proxy. Building on this, we propose AES--Adaptive Entropy Scheduling--which adaptively adjusts the entropy coefficient/temperature online using observable drift proxies during training, requiring almost no structural changes and incurring minimal overhead. Across 4 algorithm variants, 12 tasks, and 4 drift modes, AES significantly reduces the fraction of performance degradation caused by drift and accelerates recovery after abrupt changes.
title Tracking Drift: Variation-Aware Entropy Scheduling for Non-Stationary Reinforcement Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2601.19624