2000 character limit reached
A Framework for Effective AI Recommendations in Cyber-Physical-Human Systems (2403.05715v1)
Published 8 Mar 2024 in eess.SY, cs.AI, cs.HC, cs.LG, and cs.SY
Abstract: Many cyber-physical-human systems (CPHS) involve a human decision-maker who may receive recommendations from an AI platform while holding the ultimate responsibility of making decisions. In such CPHS applications, the human decision-maker may depart from an optimal recommended decision and instead implement a different one for various reasons. In this letter, we develop a rigorous framework to overcome this challenge. In our framework, we consider that humans may deviate from AI recommendations as they perceive and interpret the system's state in a different way than the AI platform. We establish the structural properties of optimal recommendation strategies and develop an approximate human model (AHM) used by the AI. We provide theoretical bounds on the optimality gap that arises from an AHM and illustrate the efficacy of our results in a numerical example.
- M. Y. Uzun, E. Inanc, and Y. Yildiz, “Enhancing human operator performance with long short-term memory networks in adaptively controlled systems,” IEEE Control Systems Letters, 2023.
- N. Venkatesh, V.-A. Le, A. Dave, and A. A. Malikopoulos, “Connected and automated vehicles in mixed-traffic: Learning human driver behavior for effective on-ramp merging,” in Proceedings of the 62nd IEEE Conference on Decision and Control (CDC). IEEE, 2023, pp. 92–97.
- A. Dave, I. V. Chremos, and A. A. Malikopoulos, “Social media and misleading information in a democracy: A mechanism design approach,” IEEE Transactions on Automatic Control, vol. 67, no. 5, pp. 2633–2639, 2022.
- H. Bang, A. Dave, and A. A. Malikopoulos, “Routing in Mixed Transportation Systems for Mobility Equity,” Proceedings of the 2024 American Control Conference, 2024 (to appear, arXiv:2309.03981).
- B. Green and Y. Chen, “The principles and limits of algorithm-in-the-loop decision making,” Proceedings of the ACM on Human-Computer Interaction, vol. 3, no. CSCW, pp. 1–24, 2019.
- A. A. Malikopoulos, “Separation of learning and control for cyber-physical systems,” Automatica, vol. 151, no. 110912, 2023.
- T. Samad, “Human-in-the-loop control and cyber–physical–human systems: applications and categorization,” Cyber–physical–human systems: fundamentals and applications, pp. 1–23, 2023.
- M. Carroll, R. Shah, M. K. Ho, T. Griffiths, S. Seshia, P. Abbeel, and A. Dragan, “On the utility of learning about humans for human-ai coordination,” Advances in neural information processing systems, vol. 32, 2019.
- A. M. Annaswamy and V. Jagadeesan Nair, “Human behavioral models using utility theory and prospect theory,” Cyber–Physical–Human Systems: Fundamentals and Applications, pp. 25–41, 2023.
- B. J. Dietvorst, J. P. Simmons, and C. Massey, “Overcoming algorithm aversion: People will use imperfect algorithms if they can (even slightly) modify them,” Management science, vol. 64, no. 3, pp. 1155–1170, 2018.
- J. Sun, D. J. Zhang, H. Hu, and J. A. Van Mieghem, “Predicting human discretion to adjust algorithmic prescription: A large-scale field experiment in warehouse operations,” Management Science, vol. 68, no. 2, pp. 846–865, 2022.
- M. Balakrishnan, K. Ferreira, and J. Tong, “Improving human-algorithm collaboration: Causes and mitigation of over-and under-adherence,” Available at SSRN 4298669, 2022.
- E. Glikson and A. W. Woolley, “Human trust in artificial intelligence: Review of empirical research,” Academy of Management Annals, vol. 14, no. 2, pp. 627–660, 2020.
- B. J. Dietvorst, J. P. Simmons, and C. Massey, “Algorithm aversion: people erroneously avoid algorithms after seeing them err.” Journal of Experimental Psychology: General, vol. 144, no. 1, p. 114, 2015.
- J. Grand-Clément and J. Pauphilet, “The best decisions are not the best advice: Making adherence-aware recommendations,” arXiv preprint arXiv:2209.01874, 2022.
- I. Faros, A. Dave, and A. A. Malikopoulos, “A q-learning approach for adherence-aware recommendations,” IEEE Control Systems Letters, vol. 7, pp. 3645–3650, 2023.
- G. Chen, X. Li, C. Sun, and H. Wang, “Learning to make adherence-aware advice,” arXiv preprint arXiv:2310.00817, 2023.
- J. Subramanian, A. Sinha, R. Seraj, and A. Mahajan, “Approximate information state for approximate planning and reinforcement learning in partially observed systems,” The Journal of Machine Learning Research, vol. 23, no. 1, pp. 483–565, 2022.
- A. Dave, I. Faros, N. Venkatesh, and A. A. Malikopoulos, “Worst-case control and learning using partial observations over an infinite time horizon,” in Proceedings of the 62nd IEEE Conference on Decision and Control (CDC). IEEE, 2023, pp. 6014–6019.
- J. Subramanian and A. Mahajan, “Approximate information state for partially observed systems,” in 2019 IEEE 58th Conference on Decision and Control (CDC). IEEE, 2019, pp. 1629–1636.
- A. A. Malikopoulos, “On team decision problems with nonclassical information structures,” IEEE Transactions on Automatic Control, vol. 68, no. 7, pp. 3915–3930, 2023.
- H. Kurniawati, D. Hsu, and W. S. Lee, “Sarsop: Efficient point-based pomdp planning by approximating optimally reachable belief spaces.” in Robotics: Science and systems, vol. 2008. Citeseer, 2008.