Journal of Control Science and Engineering / 2014 / Article / Fig 3

Research Article

An Improved Reinforcement Learning Algorithm for Cooperative Behaviors of Mobile Robots

Figure 3

The evolution of the multirobot following-surrounding behavior.
270548.fig.003a
(a) The trajectory of predators during the first twenty trials with sequential Q-learning algorithm
270548.fig.003b
(b) The trajectory of predators during the first twenty trials with the improved Q-learning algorithm
270548.fig.003c
(c) The final state of following-surrounding behaviors