Summary of Effect Of Adaptation Rate and Cost Display in a Human-ai Interaction Game, by Jason T. Isa et al.
Effect of Adaptation Rate and Cost Display in a Human-AI Interaction Game
by Jason T. Isa, Bohan Wu, Qirui Wang, Yilin Zhang, Samuel A. Burden, Lillian J. Ratliff, Benjamin J. Chasnov
First submitted to arxiv on: 26 Aug 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Computer Science and Game Theory (cs.GT); Human-Computer Interaction (cs.HC)
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 investigates how changes in an AI’s adaptive algorithm impact behavior predictions in two-player continuous games. The AI uses a gradient descent algorithm under different adaptation rates, while human participants receive cost feedback through visual displays showing current or local joint action vectors. Results show that the AI’s adaptation rate can significantly affect human behavior, shifting outcomes between game theoretic equilibriums. Slow adaptation rates lead to Nash equilibrium outcomes, while fast rates result in human-led Stackelberg equilibrium outcomes. Localized cost information shifts outcomes towards Nash. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In a study about AI and humans playing games together, scientists looked at how the AI’s algorithm affects predictions of human behavior. The AI used different learning rates, and people played with visual displays showing costs for their actions. The research found that the AI’s learning rate can greatly affect what happens in the game. If it learns slowly, it leads to a certain outcome, but if it learns quickly, it leads to another outcome. |
Keywords
» Artificial intelligence » Gradient descent
