We employ an evolutionary optimization framework that perturbs initial states to generate informative and diverse reinforcement learning (RL) policy demonstrations. A surrogate fitness function guides the optimization by combining local diversity, behavioral certainty, and global population diversity. To assess demonstration quality, we apply a set of evaluation metrics, including the reward-based optimality gap, fidelity interquartile means (IQMs), fitness composition analysis, and trajectory visualizations. Hyperparameter sensitivity is also examined to better understand the dynamics of trajectory optimization. Our findings demonstrate that optimizing trajectory selection via surrogate fitness metrics significantly improves the interpretability of RL policies in both discrete and continuous environments. In gridworld domains, evaluations reveal significantly enhanced demonstration fidelities compared to random and ablated baselines. In continuous control, the proposed framework provides valuable insights, particularly for early-stage policies, whereas fidelity-based optimization is more effective for mature policies. By refining and systematically analyzing surrogate fitness functions, this study advances the interpretability of RL models. The proposed improvements provide deeper insights into RL decision-making, benefiting applications in safety-critical and explainability-focused domains.
Altmann et al. (Mon,) studied this question.