Robust Multi-agent Communication Based on Decentralization-Oriented Adversarial Training
By: Xuyan Ma , Yawen Wang , Junjie Wang and more
Potential Business Impact:
Makes AI teams share information better, even if some signals fail.
In typical multi-agent reinforcement learning (MARL) problems, communication is important for agents to share information and make the right decisions. However, due to the complexity of training multi-agent communication, existing methods often fall into the dilemma of local optimization, which leads to the concentration of communication in a limited number of channels and presents an unbalanced structure. Such unbalanced communication policy are vulnerable to abnormal conditions, where the damage of critical communication channels can trigger the crash of the entire system. Inspired by decentralization theory in sociology, we propose DMAC, which enhances the robustness of multi-agent communication policies by retraining them into decentralized patterns. Specifically, we train an adversary DMAC\_Adv which can dynamically identify and mask the critical communication channels, and then apply the adversarial samples generated by DMAC\_Adv to the adversarial learning of the communication policy to force the policy in exploring other potential communication schemes and transition to a decentralized structure. As a training method to improve robustness, DMAC can be fused with any learnable communication policy algorithm. The experimental results in two communication policies and four multi-agent tasks demonstrate that DMAC achieves higher improvement on robustness and performance of communication policy compared with two state-of-the-art and commonly-used baselines. Also, the results demonstrate that DMAC can achieve decentralized communication structure with acceptable communication cost.
Similar Papers
Multi-Agent Conditional Diffusion Model with Mean Field Communication as Wireless Resource Allocation Planner
Artificial Intelligence
Helps phones share internet better and faster.
Learning what to say and how precisely: Efficient Communication via Differentiable Discrete Communication Learning
Multiagent Systems
Agents learn to send smarter, smaller messages.
Consensus-based Decentralized Multi-agent Reinforcement Learning for Random Access Network Optimization
Networking and Internet Architecture
Helps many devices share internet without crashing.