SafeDreamer: Safe Reinforcement Learning with World Models

Weidong Huang, Jiaming Ji, Chunhe Xia, Borong Zhang, Yaodong Yang

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Safe Reinforcement Learning, SafeRL, World Model

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: A novel algorithm for Model-based Safe Reinforcement Learning.

Abstract:

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: https://github.com/PKU-Alignment/SafeDreamer.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Primary Area: reinforcement learning

Submission Number: 7020