To improve convergence speed by making our network's architecture closer represent one of the last challenges of reinforcement learning, a definite improvement in the performance of a DQN model has been proposed by Wang and others in the following paper: Dueling network architectures for deep reinforcement learning, Z Wang, T Schaul, M Hessel, H van Hasselt, M Lanctot, and N de Freitas, 2015, arXiv preprint arXiv:1511.06581.
Deep Q-network algorithm with dueling Q-learning
Getting ready
In this recipe, we will control an inverted pendulum system using the dueling Q-learning algorithm.
