Multiagent Learning and Coordination with Clustered Deep Q-Network

By Simon Pageaud, V. Deslandres, Vassilissa Lehoux, Salima Hassas. 2019

4 citations recorded by the source corpus.

Existing decentralized learning methods entail scalability issues due to the number of agents involved. Independent Q-Learning approach proposes that each agent learns its own action-values. One drawback of this method is that the non-stationarity introduced by Independent Q-Learning limits the use of experience replay memory, needed in deep reinforcement learning methods such as Deep Q-Network. This paper presents a multiagent, multi-level solution named Clustered Deep Q-Network (CDQN) to overcome this issue.

Subfields: Artificial Intelligence, Computer Networks and Communications, Management Science and Operations Research, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Networks and Communications

In Management Science and Operations Research

In Reinforcement Learning

Citations in the corpus

QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning (2018, methodology): “Clustered Deep Q-Networks (CDQN) (Pageaud et al., 2019) use a hierarchical approach in order to scale learning to more agents and larger joint action spaces.”