Unveiling The Decisionmaking Process In Reinforcement Learning With Genetic Programming

# Unveiling the Decision-Making Process in Reinforcement Learning with Genetic Programming

**arXiv ID:** 2407.14714
**Authors:** Manuel Eberhardinger, Florian Rupp, Johannes Maucher, Setareh Maghsudi
**Published:** 2024-07-20T00:45:03Z
**Abstract:**
Despite tremendous progress, machine learning and deep learning still suffer from incomprehensible predictions. Incomprehensibility, however, is not an option for the use of (deep) reinforcement learning in the real world, as unpredictable actions can seriously harm the involved individuals. In this work, we propose a genetic programming framework to generate explanations for the decision-making process of already trained agents by imitating them with programs. Programs are interpretable and can be executed to generate explanations of why the agent chooses a particular action. Furthermore, we conduct an ablation study that investigates how extending the domain-specific language by using library learning alters the performance of the method. We compare our results with the previous state of the art for this problem and show that we are comparable in performance but require much less hardware resources and computation time.

## Skill Description

This skill is generated from the arXiv paper: Unveiling the Decision-Making Process in Reinforcement Learning with Genetic Programming (2407.14714).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2407.14714](http://arxiv.org/abs/2407.14714v1)