A Cultural Sensitive Agent for Human-Computer Negotiation . Galit Haim , Ya'akov Gal, Sarit Kraus and Michele J. Gelfand. Motivation. Buyers and seller across geographical and ethnic borders electronic commerce: crowd-sourcing: deal-of-the-day applications:
A Cultural Sensitive Agent for Human-ComputerNegotiation
Ya'akov Gal, Sarit Kraus and Michele J. Gelfand
to succeed, an agent needs to reason about how culture affects people's decision making
Goals and Challenges
Can we build an agent that will negotiate better than the people in each countries?
1. Collect data on each country
2. Use machine learning
3. Build influence diagram
Can we build proficient negotiator with no expert designed rules?
Culture sensitive agent?
CT is the right test-bed to use because it provides a task analogy to the real world
(alternating offer protocol)
Human behavior model
Predict if the other player will keep its promise
Accept or reject the proposal?
The Lebanon people in this data set almost always kept the agreements and as a result, PAL never kept agreements
There are 3 decisions that PAL needs to make:
Use backward induction over two rounds…
games were relatively shorter
people were very reliable in the training games
people were less reliable in the training games than in Lebanon
games were relatively longer
This is the first work to show that a computer agent can learn to negotiate with people in different countries