Reinforcement Learning for Human-AI Collaboration via Probabilistic Intent Inference

Effective collaboration between humans and AI agents is increasingly essential as autonomous systems take on critical roles in domains like disaster response, healthcare, and robotics. However, achieving robust human-AI collaboration remains challenging due to the uncertainty, complexity, and unpredictability of human behavior, which is often difficult to convey explicitly to AI agents. This paper presents a belief-space reinforcement learning framework that enables AI agents to implicitly and probabilistically infer latent human intentions from behavioral data and integrate this understanding into robust decision-making. Our approach models human behavior at both the action (low) and subtask (high) levels, combining these with human and agent state information to construct a comprehensive belief state for the AI agent. We demonstrate that this belief state follows the Markov property, enabling the derivation of an optimal Bayesian policy under human and task uncertainty. Deep reinforcement learning is used to train an offline Bayesian policy across a wide range of human and task uncertainties, allowing real-time deployment to support effective human-AI collaboration. Numerical experiments demonstrate the effectiveness of the proposed policy in terms of cooperation, adaptability, and robustness.

Authors

• Yuxin Lin School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen
• Seyede Fatemeh Ghoreishi
• Tian Lan George Washington University
• Mahdi Imani Northeastern University

Keywords

No keywords are indexed for this paper.