Assessing AI Utility: The Random Guesser Test for Sequential Decision-Making Systems
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909284178067456 |
|---|---|
| author | Ide, Shun Blunt, Allison Bouneffouf, Djallel |
| author_facet | Ide, Shun Blunt, Allison Bouneffouf, Djallel |
| contents | We propose a general approach to quantitatively assessing the risk and vulnerability of artificial intelligence (AI) systems to biased decisions. The guiding principle of the proposed approach is that any AI algorithm must outperform a random guesser. This may appear trivial, but empirical results from a simplistic sequential decision-making scenario involving roulette games show that sophisticated AI-based approaches often underperform the random guesser by a significant margin. We highlight that modern recommender systems may exhibit a similar tendency to favor overly low-risk options. We argue that this "random guesser test" can serve as a useful tool for evaluating the utility of AI actions, and also points towards increasing exploration as a potential improvement to such systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_20276 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Assessing AI Utility: The Random Guesser Test for Sequential Decision-Making Systems Ide, Shun Blunt, Allison Bouneffouf, Djallel Computers and Society Artificial Intelligence We propose a general approach to quantitatively assessing the risk and vulnerability of artificial intelligence (AI) systems to biased decisions. The guiding principle of the proposed approach is that any AI algorithm must outperform a random guesser. This may appear trivial, but empirical results from a simplistic sequential decision-making scenario involving roulette games show that sophisticated AI-based approaches often underperform the random guesser by a significant margin. We highlight that modern recommender systems may exhibit a similar tendency to favor overly low-risk options. We argue that this "random guesser test" can serve as a useful tool for evaluating the utility of AI actions, and also points towards increasing exploration as a potential improvement to such systems. |
| title | Assessing AI Utility: The Random Guesser Test for Sequential Decision-Making Systems |
| topic | Computers and Society Artificial Intelligence |
| url | https://arxiv.org/abs/2407.20276 |