Stackelberg Punishment and Bully-Proofing Autonomous Vehicles
This work addresses the challenge of designing bully-proof autonomous vehicles for safer human-vehicle interactions, representing an incremental improvement in applying game theory to real-world systems.
The paper tackles the problem of minimizing the cost of enforcing cooperative behavior in repeated games by introducing Stackelberg punishment, which selects a behavior that sufficiently punishes the other player while maximizing one's own score, and demonstrates its application in a virtual autonomous vehicle experiment, showing it discourages human bullying in driving scenarios.
Mutually beneficial behavior in repeated games can be enforced via the threat of punishment, as enshrined in game theory's well-known "folk theorem." There is a cost, however, to a player for generating these disincentives. In this work, we seek to minimize this cost by computing a "Stackelberg punishment," in which the player selects a behavior that sufficiently punishes the other player while maximizing its own score under the assumption that the other player will adopt a best response. This idea generalizes the concept of a Stackelberg equilibrium. Known efficient algorithms for computing a Stackelberg equilibrium can be adapted to efficiently produce a Stackelberg punishment. We demonstrate an application of this idea in an experiment involving a virtual autonomous vehicle and human participants. We find that a self-driving car with a Stackelberg punishment policy discourages human drivers from bullying in a driving scenario requiring social negotiation.