Nested Training for Mutual Adaptation in Human-AI Teaming

Mutual adaptation is essential in human–robot teaming, as humans adjust their behavior in response to the robot. Prior work trains against diverse but static partners, missing adaptive human responses, while simultaneous multi-agent learning often yields brittle coordination conventions that fail to generalize. We model human–robot teaming as a finite-Level Interactive Partially Observable Markov Decision Process (I-POMDP), explicitly representing human adaptation within the state. To approximately solve this formulation, we introduce a nested training regime in which agents at a level are trained against adaptive agents at a level below. This exposes agents to adaptation while preventing emergence of opaque coordination strategies. In the Overcooked domain with required-cooperation, our method outperforms standard baselines with unseen adaptive partners and demonstrates stronger adaptability during interaction.

Authors

• Upasana Biswas Arizona State University
• Durgesh Kalwar Arizona State University
• Subbarao Kambhampati Arizona State University
• Sarath Sreedharan Colorado State University

Keywords

• I-POMDP
• Human-AI Teaming
• Cooperative AI
• Multi-agent Reinforcement Learning