A Multiagent Reinforcement Learning Algorithm with Non-linear Dynamics
Journal or Book Title
JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH
In this paper, we consider the consensus problem of distributed multi-agent systems with nonlinear dynamics and disturbances. The underlying system is described based upon the stochastic communication network topology. To solve this problem, we propose a multi-agent reinforcement learning-based method that converts the consensus problem with multiple nonlinear agents into one learning target and automatically learns effective strategies. The actor-critic method is adopted for updating learning policies. Moreover, we design a distributed communication method to ensure that each agent in the multiagent system can obtain consensus information. Two examples are presented to show the effectiveness and potential of the proposed design technique.
Abdallah, S and Lesser, V, "A Multiagent Reinforcement Learning Algorithm with Non-linear Dynamics" (2008). JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH. 765.