Deep Q-learning represents an evolution of the basic Q-learning method. The state-action is replaced by a neural network, with the aim of approximating the optimal value function. Compared to the Q-learning approaches, where it was used to structure the network in order to request both input and action and providing its expected return, deep Q-learning revolutionizes the structure to request only the state of the environment and supply as many status-action values as there are actions that can be performed in the environment.
Implementing the deep Q-learning algorithm
Getting ready
In this recipe, we will use the deep Q-learning approaches to controls a character's movement in a grid world. In this recipe, the keras-rl...
