In the final chapter of this book, we're going to introduce algorithms that directly optimize the policy network in reinforcement learning. These algorithms are collectively referred to as policy gradient methods. Since the policy network is directly optimized during training, the policy gradient methods belong to the family of on-policy reinforcement learning algorithms. Like value-based methods that we discussed in Chapter 9, Deep Reinforcement Learning, policy gradient methods can also be implemented as deep reinforcement learning algorithms.
A fundamental motivation in studying the policy gradient methods is addressing the limitations of Q-Learning. We'll recall that Q-Learning is about selecting the action that maximizes the value of the state. With Q function, we're able to determine the policy that enables the agent to decide on which action to take for a given state. The chosen action is simply the one that gives the agent the maximum value. In...