REACT: Revealing Evolutionary Action Consequence Trajectories for Interpretable Reinforcement Learning

To enhance the interpretability of Reinforcement Learning (RL), we propose Revealing Evolutionary Action Consequence Trajectories (REACT). In contrast to the prevalent practice of validating RL models based on their optimal behavior learned during training, we posit that considering a range of edge-...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-04
Main Authors: Altmann, Philipp, Davignon, Céline, Zorn, Maximilian, Ritz, Fabian, Linnhoff-Popien, Claudia, Gabor, Thomas
Format: Article
Language:English
Subjects:
Evolutionary algorithms
Optimization
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:To enhance the interpretability of Reinforcement Learning (RL), we propose Revealing Evolutionary Action Consequence Trajectories (REACT). In contrast to the prevalent practice of validating RL models based on their optimal behavior learned during training, we posit that considering a range of edge-case trajectories provides a more comprehensive understanding of their inherent behavior. To induce such scenarios, we introduce a disturbance to the initial state, optimizing it through an evolutionary algorithm to generate a diverse population of demonstrations. To evaluate the fitness of trajectories, REACT incorporates a joint fitness function that encourages both local and global diversity in the encountered states and chosen actions. Through assessments with policies trained for varying durations in discrete and continuous environments, we demonstrate the descriptive power of REACT. Our results highlight its effectiveness in revealing nuanced aspects of RL models' behavior beyond optimal performance, thereby contributing to improved interpretability.
ISSN:2331-8422