Negotiating Team Formation Using Deep Reinforcement Learning

TL;DR

This paper introduces a deep reinforcement learning framework enabling autonomous agents to negotiate and form teams without relying on specific protocols or human input, demonstrating effectiveness across various environments.

Contribution

The authors develop a protocol-agnostic, experience-driven deep RL approach for multi-agent negotiation and team formation, addressing scalability and generality issues in prior methods.

Findings

Agents outperform hand-crafted bots in negotiation tasks.

Negotiation outcomes align with cooperative game theory predictions.

Physical location impacts negotiation results.

Abstract

When autonomous agents interact in the same environment, they must often cooperate to achieve their goals. One way for agents to cooperate effectively is to form a team, make a binding agreement on a joint plan, and execute it. However, when agents are self-interested, the gains from team formation must be allocated appropriately to incentivize agreement. Various approaches for multi-agent negotiation have been proposed, but typically only work for particular negotiation protocols. More general methods usually require human input or domain-specific data, and so do not scale. To address this, we propose a framework for training agents to negotiate and form teams using deep reinforcement learning. Importantly, our method makes no assumptions about the specific negotiation protocol, and is instead completely experience driven. We evaluate our approach on both non-spatial and spatially extended team-formation negotiation environments, demonstrating that our agents beat hand-crafted bots and reach negotiation outcomes consistent with fair solutions predicted by cooperative game theory. Additionally, we investigate how the physical location of agents influences negotiation outcomes.