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

Manuel Eberhardinger, Florian Rupp, Johannes Maucher, Setareh Maghsudi
7/20/2024
cs.AIcs.LGcs.NE

No official code found. Best implementation: ManuelEberhardinger/unveiling-rl-with-gp (3 stars, MIT, last commit 2025-05-08).

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.

View on arXivView PDF

Code Implementations(1)

ManuelEberhardinger/unveiling-rl-with-gpCommunity100%
MIT

Official repository for the paper: Unveiling the Decision-Making Process in Reinforcement Learning with Genetic Programming

30PythonMay 28, 20241 years agoMIT

Similar Papers

Human-Readable Programs as Actors of Reinforcement Learning Agents Using Critic-Moderated Evolution

85% match1 repo2024

Leveraging Genetic Algorithms for Efficient Demonstration Generation in Real-World Reinforcement Learning Environments

83% match2025

Explainable Deep Reinforcement Learning: State of the Art and Challenges

82% match2023

A Survey on Explainable Deep Reinforcement Learning

81% match2025

Genes in Intelligent Agents

80% match2023

Decision Stacks: Flexible Reinforcement Learning via Modular Generative Models

80% match1 repo122023

Cite this paper

@article{eberhardinger2024unveiling,
  title  = {Unveiling the Decision-Making Process in Reinforcement Learning with Genetic Programming},
  author = {Manuel Eberhardinger and Florian Rupp and Johannes Maucher and Setareh Maghsudi},
  year   = {2024},
  eprint = {2407.14714},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2407.14714v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2407.14714.svg)](https://codeofpaper.com/paper/2407.14714)

Discussion