Saved in:
| Main Authors: | , , , |
|---|---|
| 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 |