Constrained Attractor Selection Using Deep Reinforcement Learning

This paper describes an approach for attractor selection in nonlinear dynamical systems with constrained actuation. Attractor selection is achieved using two different deep reinforcement learning methods: 1) the cross-entropy method (CEM) and 2) the deep deterministic policy gradient (DDPG) method. The framework and algorithms for applying these control methods are presented. Experiments were performed on a Duffing oscillator as it is a classic nonlinear dynamical system with multiple attractors. Both methods achieve attractor selection under various control constraints. While these methods have nearly identical success rates, the DDPG method has the advantages a high learning rate, low performance variance, and offers a smooth control approach. This experiment demonstrates the applicability of reinforcement learning to constrained attractor selection problems.