.png){kind=icon}
.png){kind=icon}
Return
Prospective Learning in Retrospect
.png){kind=icon}
PRE
AI
DOI：10.1007/978-3-032-00686-8_3.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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.
Keywords:
Distribution Shifts
Out-of-Distribution Generalization
Learning Theory
Sequential Decision-Making
Journal
A
IF:
0
Papers:
38
Citations:
0