Comparing NARS and Reinforcement Learning: An Analysis of ONA and $Q$-Learning Algorithms

TL;DR

This paper compares NARS and RL algorithms, specifically ONA and Q-Learning, across various environments to evaluate NARS as a viable alternative to reinforcement learning in sequence-based tasks.

Contribution

It provides a comparative analysis of NARS and RL, highlighting NARS's potential as a competitive and versatile approach in diverse environments.

Findings

NARS performs competitively in simple environments.

NARS shows promising results in non-deterministic settings.

NARS can be a viable alternative to RL in sequence tasks.

Abstract

In recent years, reinforcement learning (RL) has emerged as a popular approach for solving sequence-based tasks in machine learning. However, finding suitable alternatives to RL remains an exciting and innovative research area. One such alternative that has garnered attention is the Non-Axiomatic Reasoning System (NARS), which is a general-purpose cognitive reasoning framework. In this paper, we delve into the potential of NARS as a substitute for RL in solving sequence-based tasks. To investigate this, we conduct a comparative analysis of the performance of ONA as an implementation of NARS and $Q$-Learning in various environments that were created using the Open AI gym. The environments have different difficulty levels, ranging from simple to complex. Our results demonstrate that NARS is a promising alternative to RL, with competitive performance in diverse environments, particularly in non-deterministic ones.