LLM-assisted Semantic Option Discovery for Facilitating Adaptive Deep Reinforcement Learning

ArXi:2603.01488v2 Announce Type: replace Despite achieving remarkable success in complex tasks, Deep Reinforcement Learning (DRL) is still suffering from critical issues in practical applications, such as low data efficiency, lack of interpretability, and limited cross-environment transferability. However, the learned policy generating actions based on states are sensitive to the environmental changes, struggling to guarantee behavioral safety and compliance.