# Comparing Knowledge-based Reinforcement Learning to Neural Networks in a Strategy Game

## TL;DR

This paper compares Knowledge-Based Reinforcement Learning (KB-RL) with Neural Networks in a strategy game, demonstrating KB-RL's efficiency in data use, interpretability, and superior performance in the tested AI task.

## Contribution

It introduces a KB-RL approach that encodes human knowledge, reducing data needs and providing transparent decision-making, outperforming neural networks in the experiment.

## Key findings

- KB-RL outperformed neural networks in the experiment.
- KB-RL requires less data to learn effective policies.
- KB-RL offers transparent reasoning for decisions.

## Abstract

The paper reports on an experiment, in which a Knowledge-Based Reinforcement Learning (KB-RL) method was compared to a Neural Network (NN) approach in solving a classical Artificial Intelligence (AI) task. In contrast to NNs, which require a substantial amount of data to learn a good policy, the KB-RL method seeks to encode human knowledge into the solution, considerably reducing the amount of data needed for a good policy. By means of Reinforcement Learning (RL), KB-RL learns to optimize the model and improves the output of the system. Furthermore, KB-RL offers the advantage of a clear explanation of the taken decisions as well as transparent reasoning behind the solution. The goal of the reported experiment was to examine the performance of the KB-RL method in contrast to the Neural Network and to explore the capabilities of KB-RL to deliver a strong solution for the AI tasks. The results show that, within the designed settings, KB-RL outperformed the NN, and was able to learn a better policy from the available amount of data. These results support the opinion that Artificial Intelligence can benefit from the discovery and study of alternative approaches, potentially extending the frontiers of AI.