Python Reinforcement Learning Projects

Critic script

We begin by importing certain modules from Keras: layers, optimizers, models, and the backend. These modules will help us to construct our neural network:

from keras import layers, models, optimizersfrom keras import backend as K

1. We create a class called Critic, whose object takes in the following parameters:

class Critic:    """Critic (Value) Model."""    def __init__(self, state_size, action_size):        """Initialize parameters and build model.        Params        ======            state_size (int): Dimension of each state            action_size (int): Dimension of each action        """        self.state_size = state_size        self.action_size = action_size        self.build_model()

2. Build a critic (value) network that maps state and action pairs (Q_values), and define input layers, as follows: ...