Let's look at the important components of a reinforcement learning problem, one by one:
- Agent: The agent is the one that interacts with the environment by performing necessary steps or actions.
- Environment: The environment is the one in which the agent interacts. Some of the available environments are deterministic, stochastic, fully observable, continuous, discrete, and many more.
- State: State is the condition or position in which the agent is currently exhibiting or residing. The state is usually a result of the agent's action.
- Action: This is something the agent does while interacting with the environment.
- Reward: This is the outcome of an action the agent performs to transition to a state. The reward may ...
