Summary of Data-driven Estimation Of Conditional Expectations, Application to Optimal Stopping and Reinforcement Learning, by George V. Moustakides
Data-Driven Estimation of Conditional Expectations, Application to Optimal Stopping and Reinforcement Learning
by George V. Moustakides
First submitted to arxiv on: 18 Jul 2024
Categories
- Main: Machine Learning (stat.ML)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed work introduces a simple and purely data-driven approach for estimating conditional expectations, which is essential in various stochastic optimization problems. The method aims to directly estimate the desired conditional expectation without requiring knowledge of the underlying conditional density. This extension can be applied to cases such as Optimal Stopping and Optimal Action Policy in Reinforcement Learning. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study proposes a way to calculate something called “conditional expectations” using only data, without needing to know the underlying rules that make up the data. The method is tested on two specific problems: one where you need to decide when to stop doing something, and another where you’re trying to find the best actions in a situation. |
Keywords
* Artificial intelligence * Optimization * Reinforcement learning
