paper-with-me

홈 › Papers

SafeDreamer: Safe Reinforcement Learning with World Models

2023-07-14 · Weidong Huang, Jiaming Ji, Chunhe Xia, Borong Zhang, Yaodong Yang

The deployment of Reinforcement Learning (RL) in real-world applications is constrained by its failure to satisfy safety criteria. Existing Safe Reinforcement Learning (SafeRL) methods, which rely on cost functions to enforce safety, often fail to achieve zero-cost performance in complex scenarios, especially vision-only tasks. These limitations are primarily due to model inaccuracies and inadequate sample efficiency. The integration of the world model has proven effective in mitigating these shortcomings. In this work, we introduce SafeDreamer, a novel algorithm incorporating Lagrangian-based methods into world model planning processes within the superior Dreamer framework. Our method achieves nearly zero-cost performance on various tasks, spanning low-dimensional and vision-only input, within the Safety-Gymnasium benchmark, showcasing its efficacy in balancing performance and safety in RL tasks. Further details can be found in the code repository: \url{https://github.com/PKU-Alignment/SafeDreamer}.

📄 PDF Abstract BibTeX arXiv:2307.07176

Code (1)

pku-alignment/safedreamer 공식 구현 jax

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Safe Reinforcement Learning

Methods 이 논문이 사용한 방법론

fail 설명 없음

Similar Papers 제목 키워드 기반

SafeDojo: Safe Reinforcement Learning for VLA via Interactive World Model

2026-06-15 · Kai Tang, Peidong Jia, Zhong Chu, Jixian Wu 외 arxiv

Safe control is a prerequisite for real-world embodied intelligence, for which safe reinforcement learning has emerged as a promising paradigm. However, existing safe reinforcement learning methods either require costly …

Reinforcement Learning

Predictive Safety Shield for Dyna-Q Reinforcement Learning

2025-11-26 · Jin Pin, Krasowski Hanna, Vanneaux Elena arxiv

Obtaining safety guarantees for reinforcement learning is a major challenge to achieve applicability for real-world tasks. Safety shields extend standard reinforcement learning and achieve hard safety guarantees. However…

Reinforcement Learning

Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning

2021-08-13 · Lukas Brunke, Melissa Greeff, Adam W. Hall, Zhaocong Yuan 외

The last half-decade has seen a steep rise in the number of contributions on safe learning methods for real-world robotic deployments from both the control and reinforcement learning communities. This article provides a …

Decision Makingreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1

Don't do it: Safer Reinforcement Learning With Rule-based Guidance

2022-12-28 · Ekaterina Nikonova, Cheng Xue, Jochen Renz

During training, reinforcement learning systems interact with the world without considering the safety of their actions. When deployed into the real world, such systems can be dangerous and cause harm to their surroundin…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Robot Navigation

Reinforcement Learning for Robotic Safe Control with Force Sensing

2025-10-30 · Nan Lin, Linrui Zhang, Yuxuan Chen, Zhenrui Chen 외 arxiv

For the task with complicated manipulation in unstructured environments, traditional hand-coded methods are ineffective, while reinforcement learning can provide more general and useful policy. Although the reinforcement…

Reinforcement Learning