Evaluating Actuators in a Purely Information-Theory Based Reward Model

TL;DR

This paper proposes a novel information-theoretic reward model for evaluating actuators in a cognitive engine, focusing on their impact on overall reward through sensor feedback, unlike previous models for codelet evaluation.

Contribution

It introduces a new method to evaluate actuators based on their influence on reward, extending the information-theoretic approach to include physical effectors.

Findings

Actuators are evaluated by their impact on reward via sensor feedback.

The model links actuator activation to changes in information gain and reward.

This approach enables better assessment of physical effectors in autonomous systems.

Abstract

AGINAO builds its cognitive engine by applying self-programming techniques to create a hierarchy of interconnected codelets - the tiny pieces of code executed on a virtual machine. These basic processing units are evaluated for their applicability and fitness with a notion of reward calculated from self-information gain of binary partitioning of the codelet's input state-space. This approach, however, is useless for the evaluation of actuators. Instead, a model is proposed in which actuators are evaluated by measuring the impact that an activation of an effector, and consequently the feedback from the robot sensors, has on average reward received by the processing units.