Summary of Partially Observable Contextual Bandits with Linear Payoffs, by Sihan Zeng et al.
Partially Observable Contextual Bandits with Linear Payoffs
by Sihan Zeng, Sujay Bhatt, Alec Koppel, Sumitra Ganesh
First submitted to arxiv on: 17 Sep 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Machine Learning (stat.ML)
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 In this research paper, the authors tackle a new challenge in contextual bandits by considering partially observable, correlated contexts with linear payoffs, motivated by applications in finance where market information is not fully observed. The proposed algorithmic pipeline, EMKF-Bandit, integrates system identification, filtering, and classic contextual bandit algorithms to estimate latent parameters and make decisions. The authors show that EMKF-Bandit with Thompson sampling incurs a sub-linear regret under certain conditions on filtering. Numerical simulations demonstrate the benefits and practical applicability of the proposed pipeline. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about creating a new way for computers to learn from incomplete information in financial markets. Currently, decision-making in finance relies on market data that isn’t always fully available. The authors developed an algorithm called EMKF-Bandit that combines different techniques to make better decisions with limited information. They showed that their approach can help reduce the risk of making bad choices by a significant amount. |
