Learning To Make Adherence-aware Advice

Abstract

As artificial intelligence (AI) systems play an increasingly prominent role in human decision-making, challenges surface in the realm of human-AI interactions. One challenge arises from the suboptimal AI policies due to the inadequate consideration of humans disregarding AI recommendations, as well as the need for AI to provide advice selectively when it is most pertinent. This paper presents a sequential decision-making model that (i) takes into account the human's adherence level (the probability that the human follows/rejects machine advice) and (ii) incorporates a defer option so that the machine can temporarily refrain from making advice. We provide learning algorithms that learn the optimal advice policy and make advice only at critical time stamps. Compared to problem-agnostic reinforcement learning algorithms, our specialized learning algorithms not only enjoy better theoretical convergence properties but also show strong empirical performance.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keychen2023learning

Related papers

• Reinforcement Learning With Human Advice: A Survey (2020)0.00
• Multi-agent Advisor Q-learning (2021)0.00
• Learning-to-defer For Sequential Medical Decision-making Under Uncertainty (2021)0.00
• Human Adaptation To Adaptive Machines Converges To Game-theoretic Equilibria (2023)2.26
• Opinion-guided Reinforcement Learning (2024)0.00
• Towards Optimizing Human-centric Objectives In Ai-assisted Decision-making With Offline Reinforcement Learning (2024)0.00
• Agent-aware Training For Agent-agnostic Action Advising In Deep Reinforcement Learning (2023)2.26
• Improving Human Performance With Value-aware Interventions: A Case Study In Chess (2026)0.00