Machine learning is a kind of reinforcement learning. In this scenario, an agent interacts with its surroundings by generating actions and learns through feedback. The feedback is delivered to the agent in the form of rewards, such as a positive reward for each successful activity and a negative reward for each poor action. The agent is not given any labelled data or supervision. To explore the world in RL, the agent continually performs three things: execute actions, change state, and get feedback.
The following are some of the most often used reinforcement learning algorithms:
- Q-Learning
- SARSA(State Action Reward State Action)
- Deep Q Neural Network