Summary
In this chapter, we learned how the values of various actions in a given state are calculated. We then learned how the agent updates the Q-table, using the discounted value of taking an action in a given state. In the process of doing this, we learned how the Q-table is infeasible in a scenario where the number of states is high. We also learned how to leverage deep Q-networks to address the scenario where the number of possible states is high. Then, we moved on to leveraging CNN-based neural networks while building an agent that learned how to play Pong, using a DQN based on fixed targets. Finally, we learned how to leverage a DQN with fixed targets to perform self-driving, using the CARLA simulator.
As we have seen repeatedly in this chapter, you can use deep Q-learning to learn very different tasks – such as CartPole balancing, playing Pong, and self-driving navigation – with almost the same code. While this is not the end of our journey into exploring...
