Unveiling the Decision-Making Process in Reinforcement Learning with Genetic Programming
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909263004172288 |
|---|---|
| author | Eberhardinger, Manuel Rupp, Florian Maucher, Johannes Maghsudi, Setareh |
| author_facet | Eberhardinger, Manuel Rupp, Florian Maucher, Johannes Maghsudi, Setareh |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_14714 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Unveiling the Decision-Making Process in Reinforcement Learning with Genetic Programming Eberhardinger, Manuel Rupp, Florian Maucher, Johannes Maghsudi, Setareh Artificial Intelligence Machine Learning Neural and Evolutionary Computing 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. |
| title | Unveiling the Decision-Making Process in Reinforcement Learning with Genetic Programming |
| topic | Artificial Intelligence Machine Learning Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2407.14714 |