A Decentralized Communication Framework based on Dual-Level Recurrence for Multi-Agent Reinforcement Learning

by   Jingchen Li, et al.

We propose a model enabling decentralized multiple agents to share their perception of environment in a fair and adaptive way. In our model, both the current message and historical observation are taken into account, and they are handled in the same recurrent model but in different forms. We present a dual-level recurrent communication framework for multi-agent systems, in which the first recurrence occurs in the communication sequence and is used to transmit communication data among agents, while the second recurrence is based on the time sequence and combines the historical observations for each agent. The developed communication flow separates communication messages from memories but allows agents to share their historical observations by the dual-level recurrence. This design makes agents adapt to changeable communication objects, while the communication results are fair to these agents. We provide a sufficient discussion about our method in both partially observable and fully observable environments. The results of several experiments suggest our method outperforms the existing decentralized communication frameworks and the corresponding centralized training method.


Centralized Training with Hybrid Execution in Multi-Agent Reinforcement Learning

We introduce hybrid execution in multi-agent reinforcement learning (MAR...

Decentralized Coordination in Partially Observable Queueing Networks

We consider communication in a fully cooperative multi-agent system, whe...

Inference-Based Deterministic Messaging For Multi-Agent Communication

Communication is essential for coordination among humans and animals. Th...

R-MADDPG for Partially Observable Environments and Limited Communication

There are several real-world tasks that would ben-efit from applying mul...

Multi-agent systems and decentralized artificial superintelligence

Multi-agents systems communication is a technology, which provides a way...

Multi-Agent Intention Sharing via Leader-Follower Forest

Intention sharing is crucial for efficient cooperation under partially o...

Soft Hierarchical Graph Recurrent Networks for Many-Agent Partially Observable Environments

The recent progress in multi-agent deep reinforcement learning(MADRL) ma...

Please sign up or login with your details

Forgot password? Click here to reset