Chapter 1 – Fundamentals of Reinforcement Learning
- In supervised and unsupervised learning, the model (agent) learns based on the given training dataset, whereas, in reinforcement learning (RL), the agent learns by directly interacting with the environment. Thus RL is essentially an interaction between the agent and its environment.
- The environment is the world of the agent. The agent stays within the environment. For instance, in the chess game, the chessboard is the environment since the chess player (agent) learns to play chess within the chessboard (environment). Similarly, in the Super Mario Bros game, the world of Mario is called the environment.
- The deterministic policy maps the state to one particular action, whereas the stochastic policy maps the state to the probability distribution over an action space.
- The agent interacts with the environment by performing actions, starting from the initial state until they reach the final state...