Work

Multi-View Decision Processes: The Helper-AI Problem

Year: 2017

Type: conference-paper

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.

Source: Digital Access to Scholarship at Harvard (DASH) (Harvard University)

Authors: Christos Dimitrakakis, David C. Parkes, Goran Radanović, Paul Tylkin

Institutions: Chalmers University of Technology, Harvard University

Language: English

Topic: Reinforcement Learning in Robotics

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: National Science Foundation, Future of Life Institute, European Commission, Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung

Awards: G1323383031, G3207356259, G393177772, Mobility for Regional Excellence, MoRE, G4104599821, G5702163051

OpenAlex ID: W2751659792

FWCI: 0.991

Cites: 11

Cited by: 17

Related to: 10