Surrogate Fitness Metrics for Interpretable Reinforcement Learning
This work addresses interpretability challenges in RL, particularly for safety-critical and explainability-focused domains, though it appears incremental as it refines existing methods.
The study tackled the problem of improving interpretability in reinforcement learning policies by optimizing trajectory selection using surrogate fitness metrics, resulting in significantly enhanced demonstration fidelities in gridworld domains and valuable insights for early-stage policies in continuous control.
We employ an evolutionary optimization framework that perturbs initial states to generate informative and diverse policy demonstrations. A joint 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 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 offers valuable insights, particularly for early-stage policies, while fidelity-based optimization proves 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.