Scholarlink

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.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Enhancing RL Safety with Counterfactual LLM Reasoning

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Dennis Gross,
  • Helge Spieker

摘要

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.