NegotiationGym: Self-Optimizing Agents in a Multi-Agent Social Simulation Environment
This provides a tool for researchers and developers to simulate and study multi-agent negotiation scenarios, but it is incremental as it builds upon existing simulation frameworks.
The authors tackled the problem of configuring and running multi-agent social simulations for negotiation and cooperation by designing NegotiationGym, an API and user interface that enables easy customization and self-optimizing agents through multiple interaction rounds.
We design and implement NegotiationGym, an API and user interface for configuring and running multi-agent social simulations focused upon negotiation and cooperation. The NegotiationGym codebase offers a user-friendly, configuration-driven API that enables easy design and customization of simulation scenarios. Agent-level utility functions encode optimization criteria for each agent, and agents can self-optimize by conducting multiple interaction rounds with other agents, observing outcomes, and modifying their strategies for future rounds.