React Revealing Evolutionary Action Consequence Trajectories For Interpretable Reinforcement Learning

# REACT: Revealing Evolutionary Action Consequence Trajectories for Interpretable Reinforcement Learning

**arXiv ID:** 2404.03359
**Authors:** Philipp Altmann, Céline Davignon, Maximilian Zorn, Fabian Ritz, Claudia Linnhoff-Popien, Thomas Gabor
**Published:** 2024-04-04T10:56:30Z
**Abstract:**
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.

## Skill Description

This skill is generated from the arXiv paper: REACT: Revealing Evolutionary Action Consequence Trajectories for Interpretable Reinforcement Learning (2404.03359).

## How to Use

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

## References

- [arXiv:2404.03359](http://arxiv.org/abs/2404.03359v1)