Prospective Learning in Retrospect

TL;DR

This paper explores prospective learning, a framework designed to handle changing data distributions and goals in AI, extending it to sequential decision-making and providing preliminary algorithmic improvements and numerical results.

Contribution

It advances prospective learning by improving algorithms, extending its application to foraging scenarios, and presenting initial numerical results.

Findings

Improved prospective learning algorithms

Extension to sequential decision-making in foraging

Preliminary numerical validation of proposed methods

Abstract

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.