Enhancing RL Safety with Counterfactual LLM Reasoning
Gross, Dennis, Helge Spieker · arXiv (Cornell University) · 2024
Reinforcement learning (RL) policies may exhibit unsafe behavior and are hard to explain. We use counterfactual large language model reasoning to enhance RL policy safety post-training. We show that our approach improves and helps to explain the RL policy safety.