Empowerment and State-dependent Noise: An Intrinsic Motivation for Avoiding Unpredictable Agents

Christoph Salge, Cornelius Glackin, D. Polani

Research output: Chapter in Book/Report/Conference proceedingConference contribution

138 Downloads (Pure)

Abstract

Empowerment is a recently introduced intrinsic motivation algorithm based on the embodiment of an agent and the dynamics of the world the agent is situated in. Computed as the channel capacity from an agent’s actuators to an agent’s sensors, it offers a quantitative measure of how much an agent is in control of the world it can perceive. In this paper, we expand the approximation of empowerment as a Gaussian linear channel to compute empowerment based on the covariance matrix between actuators and sensors, incorporating state dependent noise. This allows for the first time the study of continuous systems with several agents. We found that if the behaviour of another agent cannot be predicted accurately, then interacting with that agent will decrease the empowerment of the original agent. This leads to behaviour realizing
collision avoidance with other agents, purely from maximising an agent’s empowerment
Original languageEnglish
Title of host publicationAdvances in Artificial Life, ECAL 2013
EditorsPietro Lio
PublisherMIT Press
Pages118-125
Number of pages8
ISBN (Print)9780262317092
DOIs
Publication statusPublished - 2013
Event12th European Conf on the Synthesis of Living Systems - Taormina, Italy
Duration: 2 Sept 20136 Sept 2013

Conference

Conference12th European Conf on the Synthesis of Living Systems
Country/TerritoryItaly
CityTaormina
Period2/09/136/09/13

Fingerprint

Dive into the research topics of 'Empowerment and State-dependent Noise: An Intrinsic Motivation for Avoiding Unpredictable Agents'. Together they form a unique fingerprint.

Cite this