Be Selfish, But Wisely: Investigating the Impact of Agent Personality in Mixed-Motive Human-Agent Interactions

TL;DR

This paper explores how incorporating diverse agent personalities in negotiation systems improves performance and cooperation, highlighting that selfish yet considerate agents outperform others in human-agent negotiations.

Contribution

The paper introduces two novel training modifications to create agents with diverse personalities and demonstrates that selfish agents perform better in negotiations with humans.

Findings

Selfish agents outperform others in negotiation success.

Diverse personalities influence negotiation dynamics positively.

Training modifications lead to more effective human-agent interactions.

Abstract

A natural way to design a negotiation dialogue system is via self-play RL: train an agent that learns to maximize its performance by interacting with a simulated user that has been designed to imitate human-human dialogue data. Although this procedure has been adopted in prior work, we find that it results in a fundamentally flawed system that fails to learn the value of compromise in a negotiation, which can often lead to no agreements (i.e., the partner walking away without a deal), ultimately hurting the model's overall performance. We investigate this observation in the context of the DealOrNoDeal task, a multi-issue negotiation over books, hats, and balls. Grounded in negotiation theory from Economics, we modify the training procedure in two novel ways to design agents with diverse personalities and analyze their performance with human partners. We find that although both techniques show promise, a selfish agent, which maximizes its own performance while also avoiding walkaways, performs superior to other variants by implicitly learning to generate value for both itself and the negotiation partner. We discuss the implications of our findings for what it means to be a successful negotiation dialogue system and how these systems should be designed in the future.