REACT: Revealing Evolutionary Action Consequence Trajectories for Interpretable Reinforcement Learning
This work addresses interpretability for RL practitioners, but it is incremental as it builds on existing methods for analyzing model behavior.
The paper tackles the problem of enhancing interpretability in Reinforcement Learning by proposing REACT, which generates diverse edge-case trajectories through evolutionary optimization of initial state disturbances, demonstrating its effectiveness in revealing nuanced model behaviors beyond optimal performance.
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.