Summary of Sliding-window Thompson Sampling For Non-stationary Settings, by Marco Fiandri et al.
Sliding-Window Thompson Sampling for Non-Stationary Settings
by Marco Fiandri, Alberto Maria Metelli, Francesco Trovò
First submitted to arxiv on: 8 Sep 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 paper proposes two Thompson-Sampling inspired algorithms, BETA-SWTS and γ-SWGTS, to tackle sequential decision-making problems with non-stationary rewards. These restless bandits describe scenarios where the environment changes independently of the policy-maker’s actions. The authors extend and correct previous work by Trovo et al. (2020) and derive a general regret formulation for Bernoulli and Subgaussian rewards in any arbitrary restless environment. They also analyze the performance of these algorithms in two common non-stationary settings: abruptly changing and smoothly changing environments. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about making good decisions when things change unexpectedly. It’s like playing a game where the rules keep shifting, but you need to make smart moves anyway. The authors created new algorithms called BETA-SWTS and γ-SWGTS to help with this problem. They tested these algorithms in different situations where the environment changes suddenly or gradually. This research is important because it can be used in many real-life scenarios, such as predicting weather patterns or optimizing energy usage. |
