arXiv：cs.LG· Tongxi Wang·· 4 小时前
平均奖励强化学习：从单条持续轨迹中识别近优策略
Average-Reward Policy Identification from a Single Continuing Trajectory
AI 导读
针对平均奖励强化学习，研究者提出一种算法，能在单条持续轨迹中边学习边决定在哪里收集信息，并给出识别近优策略所需交互次数的上界，同时证明了与之匹配的信息论下界。结果表明，在足够高的精度下，对一大类环境而言，单轨迹学习在最坏情况下并不比无限制访问状态-动作样本更难。
正文
Abstract:In reinforcement learning, an agent must explore an unknown environment to learn how to make good decisions. Unlike methods that can freely sample any state--action pair, an agent learning from a single trajectory must spend additional time navigating between states. It is therefore natural to expect that learning from a single trajectory requires more experience. In this paper, we show that this additional cost is not always necessary. For average-reward reinforcement learning, we develop an algorithm that learns where to collect information while ensuring that the required samples can be obtained efficiently. We establish an upper bound on the number of interactions needed to identify a near-optimal policy. Furthermore, we prove a matching information theoretic lower bound, showing that, for a broad class of environments and at sufficiently high accuracy, learning from a single trajectory is no harder in the worst case than learning with unrestricted access to state action samples. Our results reveal that the additional complexity cost of navigation can be avoided by adapting information gathering requirements to how the environment provides information.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.20486 [cs.LG] |
| (or arXiv:2610.20486v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.20486 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Tongxi Wang [view email]
[v1]
Wed, 14 Oct 2026 16:57:47 UTC (80 KB)
来源：arXiv：cs.LG · arxiv.org