用预判危险状态的方式，让强化学习更安全高效。
Nightmare Dreamer: Dreaming About Unsafe States And Planning Ahead
- 用世界模型预测潜在危险，提前规划安全动作
- 在Safety Gymnasium上实现近乎零违规，效率提升20倍
- 仅需图像输入，适合机器人等高风险场景
强化学习在真实世界应用中表现优异，尤其在机器人控制领域。但安全性不足限制了其广泛应用。本文提出Nightmare Dreamer，一种基于模型的安全强化学习算法，通过学习世界模型预测潜在安全违规，并据此规划动作。该方法在最大化奖励的同时几乎杜绝安全违规。在仅使用图像观测的Safety Gymnasium任务中，相比无模型基线，效率提升近20倍。
原文摘要 · Abstract (English)
Reinforcement Learning (RL) has shown remarkable success in real-world applications, particularly in robotics control. However, RL adoption remains limited due to insufficient safety guarantees. We introduce Nightmare Dreamer, a model-based Safe RL algorithm that addresses safety concerns by leveraging a learned world model to predict potential safety violations and plan actions accordingly. Nightmare Dreamer achieves nearly zero safety violations while maximizing rewards. Nightmare Dreamer outperforms model-free baselines on Safety Gymnasium tasks using only image observations, achieving nearly a 20x improvement in efficiency.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。