Model-based reinforcement learning in differential graphical games
It addresses cooperative control of multi-agent systems with uncertain dynamics, but the results are only simulated and the method is incremental.
This paper develops a model-based reinforcement learning technique for formation tracking in multi-agent systems with uncertain heterogeneous nonlinear dynamics, using differential game theory and an actor-critic-identifier architecture. Simulation results demonstrate the performance of the proposed approach.
This paper seeks to combine differential game theory with the actor-critic-identifier architecture to determine forward-in-time, approximate optimal controllers for formation tracking in multi-agent systems, where the agents have uncertain heterogeneous nonlinear dynamics. A continuous control strategy is proposed, using communication feedback from extended neighbors on a communication topology that has a spanning tree. A model-based reinforcement learning technique is developed to cooperatively control a group of agents to track a trajectory in a desired formation. Simulation results are presented to demonstrate the performance of the developed technique.