# Risk-Sensitive Cooperative Games for Human-Machine Systems

## TL;DR

This paper introduces a risk-sensitive dynamic game framework for human-machine systems, enabling machines to learn human preferences and optimize cooperation under uncertainty and risk sensitivities.

## Contribution

It proposes a novel risk-sensitive game model that accounts for asymmetric information and heterogeneous risk preferences in human-machine interactions.

## Key findings

- Performance measures depend on risk sensitivity and uncertainty levels
- Framework applied to self-driving taxis and robo-financial advising
- Machines can adaptively learn human preferences in strategic settings

## Abstract

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.