Summary of Optimizing Risk-averse Human-ai Hybrid Teams, by Andrew Fuchs et al.
Optimizing Risk-averse Human-AI Hybrid Teams
by Andrew Fuchs, Andrea Passarella, Marco Conti
First submitted to arxiv on: 13 Mar 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- 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 approach focuses on improving performance for hybrid teams consisting of humans and AI systems by introducing a learning-based manager that delegates tasks effectively. This manager utilizes Reinforcement Learning to optimize delegation decisions, taking into account the risk-based constraints of individual agents. The team’s performance is evaluated in various grid environments with failure states, demonstrating the optimality of the proposed manager. The results show successful delegations leading to near-optimal paths in terms of path length and number of delegations. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A hybrid team combines humans and AI systems working together. As AI becomes more advanced and widely used, teams will need a way to collaborate effectively. One approach is to teach a manager how to delegate tasks between the human and AI agents. This manager learns through Reinforcement Learning, adjusting its delegation decisions based on the results. The goal is to find the best balance between delegating tasks and minimizing changes due to undesirable behavior. The team’s performance was tested in different environments with failure states, showing that the proposed manager can make good decisions and lead the team to near-optimal paths. |
Keywords
* Artificial intelligence * Reinforcement learning
