Changing the Environment Based on Empowerment as Intrinsic Motivation
Christoph Salge, Cornelius Glackin, Daniel Polani

TL;DR
This paper explores how the information-theoretic measure of agent empowerment can serve as an intrinsic motivation for agents to actively modify their environment, demonstrated through a Minecraft-inspired simulation.
Contribution
It introduces a faster, approximation-based method for computing empowerment and demonstrates its effectiveness in guiding agents to reshape their environment based on embodiment.
Findings
Empowerment can motivate agents to modify their environment meaningfully.
Sparse sampling approximation improves computational efficiency.
Environmental modifications align with agent capabilities and embodiment.
Abstract
One aspect of intelligence is the ability to restructure your own environment so that the world you live in becomes more beneficial to you. In this paper we investigate how the information-theoretic measure of agent empowerment can provide a task-independent, intrinsic motivation to restructure the world. We show how changes in embodiment and in the environment change the resulting behaviour of the agent and the artefacts left in the world. For this purpose, we introduce an approximation of the established empowerment formalism based on sparse sampling, which is simpler and significantly faster to compute for deterministic dynamics. Sparse sampling also introduces a degree of randomness into the decision making process, which turns out to beneficial for some cases. We then utilize the measure to generate agent behaviour for different agent embodiments in a Minecraft-inspired three…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
