REACT: Revealing Evolutionary Action Consequence Trajectories for Interpretable Reinforcement Learning

arXiv:2404.03359v1 Announce Type: new
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 …

abstract arxiv behavior case contrast cs.ai cs.lg cs.ne edge interpretability posit practice react reinforcement reinforcement learning training type