Skip to yearly menu bar Skip to main content


Poster

Multi-View Decision Processes: The Helper-AI Problem

Christos Dimitrakakis · David Parkes · Goran Radanovic · Paul Tylkin

Pacific Ballroom #226

Keywords: [ Planning ] [ Markov Decision Processes ] [ Decision and Control ] [ Game Theory and Computational Economics ]


Abstract:

We consider a two-player sequential game in which agents have the same reward function but may disagree on the transition probabilities of an underlying Markovian model of the world. By committing to play a specific policy, the agent with the correct model can steer the behavior of the other agent, and seek to improve utility. We model this setting as a multi-view decision process, which we use to formally analyze the positive effect of steering policies. Furthermore, we develop an algorithm for computing the agents' achievable joint policy, and we experimentally show that it can lead to a large utility increase when the agents' models diverge.

Live content is unavailable. Log in and register to view live content