PECAN: Leveraging Policy Ensemble for Context-Aware Zero-Shot Human-AI Coordination

Understand

Zero-shot human-AI coordination holds the promise of collaborating with humans without human data.

• Prevailing methods try to train the ego agent with a population of partners via self-play.
• However, these methods suffer from two problems: 1) The diversity of a population with finite partners is limited, thereby limiting the capacity of the trained ego agent to collaborate with a novel human; 2) Current methods only provide a common best response for every partner in the population, which may result in poor zero-shot coordination performance with a novel partner or humans.
• To address these issues, we first propose the policy ensemble method to increase the diversity of partners in the population, and then develop a context-aware method enabling the ego agent to analyze and identify the partner's potential policy primitives so that it can take different actions accordingly.