让机器学习适应动态变化的数据和目标，提升长期表现。
Prospective Learning in Retrospect
- 基于前瞻性学习框架，设计可适应动态环境的算法。
- 在觅食任务中验证，算法在变化环境中表现更优。
- 适合需要持续适应的新场景，如机器人、自动驾驶。
在大多数人工智能的实际应用中，数据分布和学习目标随时间不断变化。当前主流机器学习算法所依赖的“可能近似正确”（PAC）学习框架无法有效处理动态数据分布和演进的目标，常导致性能下降。前瞻性学习是一种新兴的数学框架，可部分克服上述局限。本文在此基础上提出改进算法与数值结果，并将前瞻性学习扩展至序列决策场景，特别是觅食问题。实验表明，该方法在动态环境中具备更强的适应性。代码已公开于：https://github.com/neurodata/prolearn2。
原文摘要 · Abstract (English)
In most real-world applications of artificial intelligence, the distributions of the data and the goals of the learners tend to change over time. The Probably Approximately Correct (PAC) learning framework, which underpins most machine learning algorithms, fails to account for dynamic data distributions and evolving objectives, often resulting in suboptimal performance. Prospective learning is a recently introduced mathematical framework that overcomes some of these limitations. We build on this framework to present preliminary results that improve the algorithm and numerical results, and extend prospective learning to sequential decision-making scenarios, specifically foraging. Code is available at: https://github.com/neurodata/prolearn2.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。