A distributed reinforcement learning approach for solving optimization problems
CIT'11 Proceedings of the 5th WSEAS international conference on Communications and information technology
| Hi-index | 0.00 |
In multi-agent systems, blackboard communication pro- vides an easy way for agents to communicate. However, in a distributed architecture, the blackboard is commonly im- plemented in a single node, that is the "blackboard server". This approach may work well for a small number of agents. Nevertheless, when the number of agents increases, the blackboard server becomes the bottleneck for the system scalability. In this work we propose a novel agent com- munication system based on distributed-shared mechanisms that allows the implementation of a shared address space on a distributed system, without centralizing the blackboard. Our idea is to distribute the shared data over the nodes and use a message passing sub-system, totally transparent to the agents. We implemented this idea in a multi-agent system based on social laws, and used a distributed-shared mem- ory system to handle the messaging. We created a conflict simulator, and showed that the distributed-shared mecha- nisms easy the implementation of a truly distributed black- board.