Risk-Sensitive Cooperative Games for Human-Machine Systems
This work addresses the challenge of aligning human and machine objectives in autonomous systems, which is incremental as it builds on existing game theory and risk-sensitive methods.
The paper tackles the problem of strategic interactions in human-machine systems due to asymmetric information and risk sensitivity, proposing a risk-sensitive dynamic game framework that enables machines to learn human preferences while optimizing service, with evaluation based on regret measures applied to self-driving taxis and robo-financial advising.
Autonomous systems can substantially enhance a human's efficiency and effectiveness in complex environments. Machines, however, are often unable to observe the preferences of the humans that they serve. Despite the fact that the human's and machine's objectives are aligned, asymmetric information, along with heterogeneous sensitivities to risk by the human and machine, make their joint optimization process a game with strategic interactions. We propose a framework based on risk-sensitive dynamic games; the human seeks to optimize her risk-sensitive criterion according to her true preferences, while the machine seeks to adaptively learn the human's preferences and at the same time provide a good service to the human. We develop a class of performance measures for the proposed framework based on the concept of regret. We then evaluate their dependence on the risk-sensitivity and the degree of uncertainty. We present applications of our framework to self-driving taxis, and robo-financial advising.