In Chapter 1, we briefly touched upon the concept of reinforcement learning. As we discussed there, reinforcement learning is one of the methods in which machine learning models are trained.
Reinforcement learning is the main concept behind game AI programming and models like AlphaZero and OpenAI Five (see Appendix 1), as well as applications in the robotics field.
In reinforcement learning, the AI system—typically referred to as the agent—is introduced to an environment and is given a goal to achieve. The agent is also given a set of possible actions that can be ...
