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.
Revealing Unfair Models by Mining Interpretable Evidence
Huawei Technologies Canada（华为技术加拿大公司）；McMaster University（麦克马斯特大学）；University of British Columbia（不列颠哥伦比亚大学）；Simon Fraser University（西蒙弗雷泽大学）；Tianjin University（天津大学）
FDN: Interpretable Spatiotemporal Forecasting with Future Decomposition Networks
Department of Intelligent Systems Engineering, Indiana University Bloomington（印第安纳大学布卢明顿分校智能系统工程系）；Department of Computer Science and Engineering, Texas A&M University（德克萨斯大学阿姆斯特朗分校计算机科学与工程系）
Markov Regime-Switching Intelligent Driver Model for Interpretable Car-Following Behavior
Department of Civil Engineering, McGill University, Montreal, QC H3A 0C3, Canada；Laboratory for Information \& Decision Systems (LIDS), Massachusetts Institute of Technology, Cambridge, MA 02139, USA
