NARS vs. Reinforcement learning: ONA vs. Q-Learning

TL;DR

This paper compares NARS and reinforcement learning, specifically Q-Learning and ONA, to evaluate if NARS can serve as an alternative in sequential decision tasks using OpenAI gym environments.

Contribution

It investigates the potential of NARS as a substitute for RL by empirically comparing Q-Learning and ONA in standard environments.

Findings

NARS shows competitive performance with RL methods.

NARS demonstrates potential as an alternative in certain tasks.

The comparison provides insights into the strengths and limitations of NARS.

Abstract

One of the realistic scenarios is taking a sequence of optimal actions to do a task. Reinforcement learning is the most well-known approach to deal with this kind of task in the machine learning community. Finding a suitable alternative could always be an interesting and out-of-the-box matter. Therefore, in this project, we are looking to investigate the capability of NARS and answer the question of whether NARS has the potential to be a substitute for RL or not. Particularly, we are making a comparison between $Q$-Learning and ONA on some environments developed by an Open AI gym. The source code for the experiments is publicly available in the following link: \url{https://github.com/AliBeikmohammadi/OpenNARS-for-Applications/tree/master/misc/Python}.