Pilot: Winner of the Human-Agent Negotiation Challenge at IJCAI 2020
This work addresses the challenge of developing effective negotiation agents for human interaction, but it appears incremental as it builds on existing frameworks and prior research.
The authors tackled the problem of creating a virtual human agent for sequential negotiations with humans, resulting in Pilot winning the Human-Agent Negotiation Challenge at IJCAI 2020.
This document describes our agent Pilot, winner of the Human-Agent Negotiation Challenge at ANAC, IJCAI 2020. Pilot is a virtual human that participates in a sequence of three negotiations with a human partner. Our system is based on the Interactive Arbitration Guide Online (IAGO) negotiation framework. We leverage prior Affective Computing and Psychology research in negotiations to guide various key principles that define the behavior and personality of our agent.