LEARNING, EXPLORATION AND CHAOTIC POLICIES
ALEXEI B. POTAPOV, Mazhar Ali · International Journal of Modern Physics C · 2000
We consider different versions of exploration in reinforcement learning. For the test problem, we use navigation in a shortcut maze. It is shown that chaotic ∊-greedy policy may be as efficient as a random one. The best results were obtained with a model chaotic neuron. Therefore, exploration strategy can be implemented in a deterministic learning system such as a neural network.