A Q-learning method based on Quantum-Behaved Particle Swarm Optimizer

Normalized radial basis function (NRBF) neural network is presented to directly approach the Q-value function and generalize the information learnt by learning agent in continuous space. The action which impacts on environment is the one with maximum output of NRBF in the current state, and generated through Quantum-Behaved Particle Swarm Optimizer based on the current state. The effectiveness of the proposed Q-learning method is shown through simulation on inverted pendulum balancing problem.