Published November 22, 2022 | Version 1.0
Journal article Open

Human-Level Play in the Game of Diplomacy by Combining Language Models with Strategic Reasoning

Authors/Creators

  • 1. Meta AI
  • 2. Meta AI, Carnegie Mellon University
  • 3. Meta AI, Massachusetts Institute of Technology
  • 4. Meta AI, Columbia University
  • 5. Meta AI, University of California Berkeley
  • 6. Meta AI, Harvard University
  • 7. Meta AI, Stanford University

Description

Despite much progress in training AI systems to imitate human language, building agents that use language to communicate intentionally with humans in interactive environments remains a major challenge. We introduce CICERO, the first AI agent to achieve human-level performance in Diplomacy, a strategy game involving both cooperation and competition that emphasizes natural language negotiation and tactical coordination between seven players. CICERO integrates a language model with planning and reinforcement learning algorithms by inferring players' beliefs and intentions from its conversations and generating dialogue in pursuit of its plans. Across 40 games of an anonymous online Diplomacy league, CICERO achieved more than double the average score of the human players and ranked in the top 10% of participants who played more than one game.

Files

diplomacy_paper_figure_table_data.zip

Files (52.7 MB)

Name Size Download all
md5:8eb648799790be6c2f1b7d8c6cec04ef
52.7 MB Preview Download