Towards Deployment of Robust AI Agents for Human-Machine Partnerships
This work addresses the challenge of deploying AI agents, such as virtual assistants, that must adapt to unknown user types for effective collaboration, representing an incremental improvement in robust human-machine interaction.
The paper tackles the problem of designing AI agents that can robustly cooperate with new users in human-machine partnerships, showing that non-adaptive agents can perform arbitrarily poorly and developing two algorithms that adapt policies based on user behavior to facilitate efficient cooperation.
We study the problem of designing AI agents that can robustly cooperate with people in human-machine partnerships. Our work is inspired by real-life scenarios in which an AI agent, e.g., a virtual assistant, has to cooperate with new users after its deployment. We model this problem via a parametric MDP framework where the parameters correspond to a user's type and characterize her behavior. In the test phase, the AI agent has to interact with a user of unknown type. Our approach to designing a robust AI agent relies on observing the user's actions to make inferences about the user's type and adapting its policy to facilitate efficient cooperation. We show that without being adaptive, an AI agent can end up performing arbitrarily bad in the test phase. We develop two algorithms for computing policies that automatically adapt to the user in the test phase. We demonstrate the effectiveness of our approach in solving a two-agent collaborative task.