Keywords: Safe, Multi-agent Reinforcement Learning, Augmentation
TL;DR: CAMA can combine any SOTA non-safe MARL algorithms to ensure they satisfied added constraints without strong assumptions and complex implementations.
Abstract: With the widespread application of multi-agent reinforcement learning (MARL) in real-life settings, the ability to meet safety constraints has become an urgent problem to solve. For example, it is necessary to avoid collisions to reach a common goal in controlling multiple drones. We address this problem by introducing the Constraint Augmented Multi-Agent framework --- CAMA. CAMA can serve as a plug-and-play module to the popular MARL algorithms, including centralized training, decentralized execution and independent learning frameworks. In our approach, we represent the safety constraint as the sum of discounted safety costs bounded by the predefined value, which we call the safety budget. Experiments demonstrate that CAMA can converge quickly to a high degree of constraint satisfaction and surpasses other state-of-the-art safety counterpart algorithms in both cooperative and competitive settings.
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.
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
Submission Guidelines: Yes
Please Choose The Closest Area That Your Submission Falls Into: Social Aspects of Machine Learning (eg, AI safety, fairness, privacy, interpretability, human-AI interaction, ethics)