Changing the Environment Based on Empowerment as Intrinsic Motivation

by   Christoph Salge, et al.

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 dimensional block world. The paradigmatic results demonstrate that empowerment can be used as a suitable generic intrinsic motivation to not only generate actions in given static environments, as shown in the past, but also to modify existing environmental conditions. In doing so, the emerging strategies to modify an agent's environment turn out to be meaningful to the specific agent capabilities, i.e., de facto to its embodiment.



There are no comments yet.


page 17

page 21

page 22


Emergence of Structured Behaviors from Curiosity-Based Intrinsic Motivation

Infants are experts at playing, with an amazing ability to generate nove...

Quantifying environment and population diversity in multi-agent reinforcement learning

Generalization is a major challenge for multi-agent reinforcement learni...

Information is Power: Intrinsic Control via Information Capture

Humans and animals explore their environment and acquire useful skills e...

Learning Efficient Representation for Intrinsic Motivation

Mutual Information between agent Actions and environment States (MIAS) q...

MULEX: Disentangling Exploitation from Exploration in Deep RL

An agent learning through interactions should balance its action selecti...

Accelerating Empowerment Computation with UCT Tree Search

Models of intrinsic motivation present an important means to produce sen...

Control What You Can: Intrinsically Motivated Task-Planning Agent

We present a novel intrinsically motivated agent that learns how to cont...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.